Tootfinder

@… don't use it

@… You have a bright future ahead of you!

Edmund Burke, describing DOGE.

Gute Nacht!

Guten Morgen Wedding! Usedomer Straße

#nytimes introduced Midi crosswords via their newsletter this week. So far, so cool!
But how do I find the current one rather than adjusting the URL from the first one via newsletter to today’s date? I cannot see Midi anywhere on the #nytgames website nor in the app.

The dove pair that nest in our eaves just successfully raised these two chicks. They were alone on the nest yesterday and were gone today. They raised a single chick on the same nest earlier this year. Very clean, we see the family return every year. #naturephotography #birdphotography

Oh lordy, what a timeline.

Various thi.ng updates, bug fixes, additions and new version of https://github.com/thi-ng/zig-thing/ — now fully compatible with current Zig v0.14.1
On a more diary/devlog note: I also updated several of my Zig based work-in-progress art pieces to the latest version (some of them not touc…

The refurbished sign (2006) for The Only Sea Foods Restaurant at 20 East Hastings Street.
#yvr #vancouver #Neon

🤡
https://mobil.osnabrueck.de/de/aktuelles/bedeutender-schritt-fuer-oepnv-in-stadt-und-landkreis-beteiligungsverfahren-zum-5-nahverkehrsplan-startet-in-kuerze/…

„LLMs promise that you can be a part of a community and all the status and clout that comes with without putting in the work. And I do not see that there is a path to mend that foundational issue.“
https://tante.cc/2025/07/21/but-will-they/

🥳 New Kitten Release
• Improved Markdown parser
Kitten’s JavaScript tagged template strings (`kitten.html`) no longer fail to render as expected when interpolated values are used inside of Markdown where the Markdown render changes source order.
So, for example, the following will now work correctly, whereas, previously, the link source and link text would have been erroneously flipped:
kitten.html`
<markdown>
[${linkText}](${linkSource})
…

app/CHANGELOG.md at main
app - A web development kit that’s small, purrs, and loves you.

A new XML conversion process for mensural music encoding : CMME\_to\_MEI (via Verovio)
David Fiala (CESR), Laurent Pugin (KNAW), Marnix van Berchum (KNAW), Martha Thomae (NOVA), K\'evin Roger (CESR, UL, CRULH)
https://arxiv.org/abs/2507.15991

A new XML conversion process for mensural music encoding : CMME\_to\_MEI (via Verovio)
The Ricercar Lab - the musicological research team at the Center for advanced Studies in the Renaissance at the University of Tours - has decided to make available in open access, thanks to the support of the French digital infrastructure Biblissima, a large corpus of about 3500 XML files of 15th-c. music. This corpus was produced by the German musicologist Clemens Goldberg who encoded since 2010 onwards the musical content of 34 major 15th-c. music manuscripts and other complementary files, in…

#ShamelesslyStolenFromTumblr

Replaced article(s) found for cond-mat.stat-mech. https://arxiv.org/list/cond-mat.stat-mech/new
[1/1]:
- Quantum Potts Models on the Sierpi\'nski Pyramid
Kr\v{c}m\'ar, Zelenayov\'a, Genzor, Caha, Rap\v{c}an, Nishino, Gendiar

Pretty happy with this Spongebob I drew from memory! 🧽

A personal update, I’m going to be based in Europe for most of the next two months. I’m currently in Weymouth UK setting up a long term rental home for us (we got tired of random AirBnBs) close to my aging parents. My father is in a care home now, and my mother is adjusting to it…

Nonlinear Framework for Speech Bandwidth Extension
Tarikul Islam Tamiti, Nursad Mamun, Anomadarshi Barua
https://arxiv.org/abs/2507.15970 https://

Nonlinear Framework for Speech Bandwidth Extension
Recovering high-frequency components lost to bandwidth constraints is crucial for applications ranging from telecommunications to high-fidelity audio on limited resources. We introduce NDSI-BWE, a new adversarial Band Width Extension (BWE) framework that leverage four new discriminators inspired by nonlinear dynamical system to capture diverse temporal behaviors: a Multi-Resolution Lyapunov Discriminator (MRLD) for determining sensitivity to initial conditions by capturing deterministic chaos, …

There is no spoon.

Tensor network calculation of boundary and corner magnetization
Roman Krcmar, Jozef Genzor, Andrej Gendiar, Tomotoshi Nishino
https://arxiv.org/abs/2506.17194

Tensor network calculation of boundary and corner magnetization
The Corner Transfer Matrix Renormalization Group (CTMRG) algorithm is modified to measure the magnetization at the boundary of the system, including the corners of the square-shaped lattice. Using automatic differentiation, we calculate the magnetization's first derivative, allowing us to determine the boundary critical exponent $β$ accurately.

[2025-07-23 Wed (UTC), 9 new articles found for cs.SD Sound]
toXiv_bot_toot

Steve Irwin died as he lived - with animals in his heart.
#ShamelesslyStolenFromTheOtherSite

Partition function for several Ising model interface structures
Alessio Squarcini, Piotr Nowakowski, Douglas B. Abraham, Anna Macio{\l}ek
https://arxiv.org/abs/2506.17170

Partition function for several Ising model interface structures
We employ a procedure that enables us to calculate the excess free energies for a finite Ising cylinder with domain walls analytically. This procedure transparently covers all possible configurations of the domain walls under given boundary conditions and allows for a physical interpretation in terms of coarse-grained quantities such as surface and point tensions. The resulting integrals contain all the information about finite-size effects; we extract them by careful asymptotic analysis using …

Replaced article(s) found for cs.SD. https://arxiv.org/list/cs.SD/new
[1/1]:
- ReMi: A Random Recurrent Neural Network Approach to Music Production
Hugo Chateau-Laurent, Tara Vanhatalo, Wei-Tung Pan, Xavier Hinaut

from
https[:]//bsky.app/profile/sadiston.bsky.social/post/3kopghk5ljl23
#ShamelesslyStolenFromBlueSky

Phase Transition of the Ising Model on a 3-Dimensional Fractal Lattice
Jozef Genzor, Roman Kr\v{c}m\'ar, Hiroshi Ueda, Denis Kochan, Andrej Gendiar, Tomotoshi Nishino
https://arxiv.org/abs/2506.17053

Phase Transition of the Ising Model on a 3-Dimensional Fractal Lattice
The critical behavior of the classical Ising model on a three-dimensional fractal lattice with Hausdorff dimension $d_H = \ln32 / \ln4 = 2.5$ is investigated using the higher-order tensor renormalization group (HOTRG) method. We determine the critical temperature $T_c \approx 2.65231$ and the critical exponents for magnetization $β\approx 0.059$ and field response $δ\approx 35$. Unlike a previously studied 2D fractal with $d_H \approx 1.792$, the specific heat for this 3D fractal exhibits a d…

SALM: Spatial Audio Language Model with Structured Embeddings for Understanding and Editing
Jinbo Hu, Yin Cao, Ming Wu, Feiran Yang, Jun Yang
https://arxiv.org/abs/2507.16724

SALM: Spatial Audio Language Model with Structured Embeddings for Understanding and Editing
Spatial audio understanding is essential for accurately perceiving and interpreting acoustic environments. However, existing audio-language models struggle with processing spatial audio and perceiving spatial acoustic scenes. We introduce the Spatial Audio Language Model (SALM), a novel framework that bridges spatial audio and language via multi-modal contrastive learning. SALM consists of a text encoder and a dual-branch audio encoder, decomposing spatial sound into semantic and spatial compon…

Mean-field and Monte Carlo Analysis of Multi-Species Dynamics of agents
Eduardo Velasco Stock, Roberto da Silva, Sebastian Gon\c{c}alves
https://arxiv.org/abs/2506.16717

Mean-field and Monte Carlo Analysis of Multi-Species Dynamics of agents
We propose a mean-field (MF) approximation for the recurrence relation governing the dynamics of $m$ species of particles on a square lattice, and we simultaneously perform Monte Carlo (MC) simulations under identical initial conditions to emulate the intricate motion observed in environments such as subway corridors and scramble crossings in large cities. Each species moves according to transition probabilities influenced by its respective static floor field and the state of neighboring cells.…

TTMBA: Towards Text To Multiple Sources Binaural Audio Generation
Yuxuan He, Xiaoran Yang, Ningning Pan, Gongping Huang
https://arxiv.org/abs/2507.16564 ht…

TTMBA: Towards Text To Multiple Sources Binaural Audio Generation
Most existing text-to-audio (TTA) generation methods produce mono outputs, neglecting essential spatial information for immersive auditory experiences. To address this issue, we propose a cascaded method for text-to-multisource binaural audio generation (TTMBA) with both temporal and spatial control. First, a pretrained large language model (LLM) segments the text into a structured format with time and spatial details for each sound event. Next, a pretrained mono audio generation network create…

Crystal Nucleation Kinetics and Mechanism: Influence of Interaction Potential
Porhouy Minh, Steven W. Hall, Ryan S. DeFever, Sapna Sarupria
https://arxiv.org/abs/2506.16541

Crystal Nucleation Kinetics and Mechanism: Influence of Interaction Potential
Modulating liquid-to-solid transitions and the resulting crystalline structure for tailored properties is much desired. Colloidal systems are exemplary to this end, but the fundamental knowledge gaps in relating the influence of intermolecular interactions to crystallization behavior continue to hinder progress. In this study, we address this knowledge gap by studying nucleation and growth in systems with modified Lennard-Jones potential. Specifically, we study the commonly used 12-6 potential …

Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries
Pengfei Cai, Yan Song, Qing Gu, Nan Jiang, Haoyu Song, Ian McLoughlin
https://arxiv.org/abs/2507.16343

Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries
Most existing sound event detection~(SED) algorithms operate under a closed-set assumption, restricting their detection capabilities to predefined classes. While recent efforts have explored language-driven zero-shot SED by exploiting audio-language models, their performance is still far from satisfactory due to the lack of fine-grained alignment and cross-modal feature fusion. In this work, we propose the Detect Any Sound Model (DASM), a query-based framework for open-vocabulary SED guided by …

Transfer-matrix approach to the Blume-Capel model on the triangular lattice
Dimitrios Mataragkas, Alexandros Vasilopoulos, Nikolaos G. Fytas, Dong-Hee Kim
https://arxiv.org/abs/2506.16483

Transfer-matrix approach to the Blume-Capel model on the triangular lattice
We investigate the spin-$1$ Blume-Capel model on an infinite strip of the triangular lattice using the transfer-matrix method combined with a sparse-matrix factorization technique. Through finite-size scaling analysis of numerically exact spectra for strip widths up to $L = 19$, we accurately locate the tricritical point improving upon recent Monte Carlo estimates. In the first-order regime, we observe exponential scaling of the spectral gap, reflecting the linear growth of interfacial tension …

Robust Bioacoustic Detection via Richly Labelled Synthetic Soundscape Augmentation
Kaspar Soltero, Tadeu Siqueira, Stefanie Gutschmidt
https://arxiv.org/abs/2507.16235

Robust Bioacoustic Detection via Richly Labelled Synthetic Soundscape Augmentation
Passive Acoustic Monitoring (PAM) analysis is often hindered by the intensive manual effort needed to create labelled training data. This study introduces a synthetic data framework to generate large volumes of richly labelled training data from very limited source material, improving the robustness of bioacoustic detection models. Our framework synthesises realistic soundscapes by combining clean background noise with isolated target vocalisations (little owl), automatically generating dynamic…

A General Framework for Linking Free and Forced Fluctuations via Koopmanism
Valerio Lucarini, Manuel Santos Gutierrez, John Moroney, Niccol\`o Zagli
https://arxiv.org/abs/2506.16446

A General Framework for Linking Free and Forced Fluctuations via Koopmanism
The link between forced and free fluctuations for nonequilibrium systems can be described via a generalized version of the celebrated fluctuation-dissipation theorem. The use of the formalism of the Koopman operator makes it possible to deliver an intepretable form of the response operators written as a sum of exponentially decaying terms, each associated one-to-one with a mode of natural variability of the system. Here we showcase on a stochastically forced version of the celebrated Lorenz '63…

LENS-DF: Deepfake Detection and Temporal Localization for Long-Form Noisy Speech
Xuechen Liu, Wanying Ge, Xin Wang, Junichi Yamagishi
https://arxiv.org/abs/2507.16220

LENS-DF: Deepfake Detection and Temporal Localization for Long-Form Noisy Speech
This study introduces LENS-DF, a novel and comprehensive recipe for training and evaluating audio deepfake detection and temporal localization under complicated and realistic audio conditions. The generation part of the recipe outputs audios from the input dataset with several critical characteristics, such as longer duration, noisy conditions, and containing multiple speakers, in a controllable fashion. The corresponding detection and localization protocol uses models. We conduct experiments b…

Method of canonical transformations in the theory of quantum gases interacting with radiation
M. S. Bulakhov, A. S. Peletminskii, P. P. Kostrobij, I. A. Ryzha, Yu. V. Slyusarenko
https://arxiv.org/abs/2506.16439

Method of canonical transformations in the theory of quantum gases interacting with radiation
An approach to the theoretical study of effects and phenomena in quantum gases interacting with radiation is proposed. The approach is based on a modification of the canonical transformation method, which was once used to diagonalize Hamiltonians describing the interaction of electrons with phonons in a solid. The capabilities of the method are demonstrated by studying the influence of photons on the spectral characteristics of atoms of quantum gases interacting with radiation. Within the frame…

LABNet: A Lightweight Attentive Beamforming Network for Ad-hoc Multichannel Microphone Invariant Real-Time Speech Enhancement
Haoyin Yan, Jie Zhang, Chengqian Jiang, Shuang Zhang
https://arxiv.org/abs/2507.16190

LABNet: A Lightweight Attentive Beamforming Network for Ad-hoc Multichannel Microphone Invariant Real-Time Speech Enhancement
Multichannel speech enhancement (SE) aims to restore clean speech from noisy measurements by leveraging spatiotemporal signal features. In ad-hoc array conditions, microphone invariance (MI) requires systems to handle different microphone numbers and array geometries. From a practical perspective, multichannel recordings inevitably increase the computational burden for edge-device applications, highlighting the necessity of lightweight and efficient deployments. In this work, we propose a light…

Endoreversible Stirling cycles: plasma engines at maximal power
Gregory Behrendt, Sebastian Deffner
https://arxiv.org/abs/2506.16303 https://

Endoreversible Stirling cycles: plasma engines at maximal power
Endoreversible engine cycles are a cornerstone of finite-time thermodynamics. We show that endoreversible Stirling engines operating with a one-component plasma as working medium run at maximal power output with the Curzon-Ahlborn efficiency. As a main result, we elucidate that this is actually a consequence of the fact that the caloric equation of state depends only linearly on temperature and only additively on volume. In particular, neither the exact form of the mechanical equation of state,…

SDBench: A Comprehensive Benchmark Suite for Speaker Diarization
Eduardo Pacheco, Atila Orhon, Berkin Durmus, Blaise Munyampirwa, Andrey Leonov
https://arxiv.org/abs/2507.16136

SDBench: A Comprehensive Benchmark Suite for Speaker Diarization
Even state-of-the-art speaker diarization systems exhibit high variance in error rates across different datasets, representing numerous use cases and domains. Furthermore, comparing across systems requires careful application of best practices such as dataset splits and metric definitions to allow for apples-to-apples comparison. We propose SDBench (Speaker Diarization Benchmark), an open-source benchmark suite that integrates 13 diverse datasets with built-in tooling for consistent and fine-gr…

Correcting systematic errors in the likelihood optimization of underdamped Langevin models of molecular dynamics trajectories
David Daniel Girardier, Hadrien Vroylandt, Sara Bonella, Fabio Pietrucci
https://arxiv.org/abs/2506.16272

Correcting systematic errors in the likelihood optimization of underdamped Langevin models of molecular dynamics trajectories
Since Kramers' pioneering work in 1940, significant efforts have been devoted to studying Langevin equations applied to physical and chemical reactions projected onto few collective variables, with particular focus on the inference of their parameters. While the inference for overdamped Langevin equations is well-established and widely applied, a notable gap remains in the literature for underdamped Langevin equations, which incorporate inertial effects and velocities. This gap arises from the …

Audio-Vision Contrastive Learning for Phonological Class Recognition
Daiqi Liu, Tom\'as Arias-Vergara, Jana Hutter, Andreas Maier, Paula Andrea P\'erez-Toro
https://arxiv.org/abs/2507.17682

Audio-Vision Contrastive Learning for Phonological Class Recognition
Accurate classification of articulatory-phonological features plays a vital role in understanding human speech production and developing robust speech technologies, particularly in clinical contexts where targeted phonemic analysis and therapy can improve disease diagnosis accuracy and personalized rehabilitation. In this work, we propose a multimodal deep learning framework that combines real-time magnetic resonance imaging (rtMRI) and speech signals to classify three key articulatory dimensio…

Microcanonical simulated annealing: Massively parallel Monte Carlo simulations with sporadic random-number generation
M. Bernaschi, L. A. Fernandez, I. Gonz\'alez-Adalid Pemart\'in, E. Marinari, V. Martin-Mayor, G. Parisi, F. Ricci-Tersenghi, J. J. Ruiz-Lorenzo, D. Yllanes
https://arxiv.org/abs/2506.16240

Microcanonical simulated annealing: Massively parallel Monte Carlo simulations with sporadic random-number generation
Numerical simulations of models and theories that describe complex experimental systems $\unicode{x2014}$in fields like high-energy and condensed-matter physics$\unicode{x2014}$ are becoming increasingly important. Examples include lattice gauge theories, which can describe, among others, quantum chromodynamics (the Standard Model description of strong interactions between elementary particles), and spin-glass systems. Beyond fundamental research, these computational methods also find practical…

BoSS: Beyond-Semantic Speech
Qing Wang, Zehan Li, Hang Lv, Hongjie Chen, Yaodong Song, Jian Kang, Jie Lian, Jie Li, Yongxiang Li, Zhongjiang He, Xuelong Li
https://arxiv.org/abs/2507.17563

BoSS: Beyond-Semantic Speech
Human communication involves more than explicit semantics, with implicit signals and contextual cues playing a critical role in shaping meaning. However, modern speech technologies, such as Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) often fail to capture these beyond-semantic dimensions. To better characterize and benchmark the progression of speech intelligence, we introduce Spoken Interaction System Capability Levels (L1-L5), a hierarchical framework illustrated the evolution…

Validity of generalized Gibbs ensemble in a random matrix model with a global $\mathbb{Z}_2$-symmetry
Adway Kumar Das
https://arxiv.org/abs/2506.16176 http…

Validity of generalized Gibbs ensemble in a random matrix model with a global $\mathbb{Z}_2$-symmetry
$\mathbb{Z}_2$ symmetry is ubiquitous in quantum mechanical systems where it drives various phase transitions and emergent physics. To understand the role of $\mathbb{Z}_2$ symmetry in the thermalization of a local observable in a disordered system, we consider random symmetric centrosymmetric (SC) matrices where the exchange symmetry is conserved. Such a conservation law splits the Hilbert space into decoupled subspaces such that the energy spectrum of a SC matrix is a superposition of two pur…

Application of Whisper in Clinical Practice: the Post-Stroke Speech Assessment during a Naming Task
Milena Davudova, Ziyuan Cai, Valentina Giunchiglia, Dragos C. Gruia, Giulia Sanguedolce, Adam Hampshire, Fatemeh Geranmayeh
https://arxiv.org/abs/2507.17326

Application of Whisper in Clinical Practice: the Post-Stroke Speech Assessment during a Naming Task
Detailed assessment of language impairment following stroke remains a cognitively complex and clinician-intensive task, limiting timely and scalable diagnosis. Automatic Speech Recognition (ASR) foundation models offer a promising pathway to augment human evaluation through intelligent systems, but their effectiveness in the context of speech and language impairment remains uncertain. In this study, we evaluate whether Whisper, a state-of-the-art ASR foundation model, can be applied to transcri…

Microstates : Do the outliers worth
Olivier Sire
https://arxiv.org/abs/2506.16080 https://arxiv.org/pdf/2506.16080

Microstates : Do the outliers worth
This note addresses the relevance of rare events in system dynamics, inspired by Jill North reflections on the origin of the arrow of time in thermodynamics. After identifying the existence of rare events, characterized by a Pareto distribution, within a simple gas particle simulation, we investigate their impact on entropy evolution. These rare events are associated with microstates that locally decrease entropy, in contrast to the overall entropy increase observed in the bulk of the system. W…

On Temporal Guidance and Iterative Refinement in Audio Source Separation
Tobias Morocutti, Jonathan Greif, Paul Primus, Florian Schmid, Gerhard Widmer
https://arxiv.org/abs/2507.17297

On Temporal Guidance and Iterative Refinement in Audio Source Separation
Spatial semantic segmentation of sound scenes (S5) involves the accurate identification of active sound classes and the precise separation of their sources from complex acoustic mixtures. Conventional systems rely on a two-stage pipeline - audio tagging followed by label-conditioned source separation - but are often constrained by the absence of fine-grained temporal information critical for effective separation. In this work, we address this limitation by introducing a novel approach for S5 th…

Unifying renormalized and bare viscosity in two-dimensional molecular dynamics simulations
Kazuma Yokota, Masato Itami, Shin-ichi Sasa
https://arxiv.org/abs/2506.16002

Unifying renormalized and bare viscosity in two-dimensional molecular dynamics simulations
Fluctuating hydrodynamics provides a framework connecting mesoscopic fluctuations with macroscopic transport behavior. To bridge mesoscopic and macroscopic transport from microscopic dynamics, we introduce a wavenumber-dependent viscosity, defined via the equilibrium correlation of time-averaged Fourier components of the fine-grained shear stress field, as a finite-wavevector extension of the Green--Kubo formula. Two-dimensional molecular dynamics simulations reveal its small-wavenumber diverge…

Weak Supervision Techniques towards Enhanced ASR Models in Industry-level CRM Systems
Zhongsheng Wang, Sijie Wang, Jia Wang, Yung-I Liang, Yuxi Zhang, Jiamou Liu
https://arxiv.org/abs/2507.16843

Weak Supervision Techniques towards Enhanced ASR Models in Industry-level CRM Systems
In the design of customer relationship management (CRM) systems, accurately identifying customer types and offering personalized services are key to enhancing customer satisfaction and loyalty. However, this process faces the challenge of discerning customer voices and intentions, and general pre-trained automatic speech recognition (ASR) models make it difficult to effectively address industry-specific speech recognition tasks. To address this issue, we innovatively proposed a solution for fin…

Generalized Spectral Statistics in the Kicked Ising model
Divij Gupta, Brian Swingle
https://arxiv.org/abs/2506.15816 https://arxiv.o…

Generalized Spectral Statistics in the Kicked Ising model
The kicked Ising model has been studied extensively as a model of quantum chaos. Bertini, Kos, and Prosen studied the system in the thermodynamic limit, finding an analytic expression for the spectral form factor, $K(t)$, at the self-dual point with periodic boundary conditions. The spectral form factor is the 2nd moment of the trace of the time evolution operator, and we study the higher moments of this random variable in the kicked Ising model. A previous study of these higher moments by Flac…

[2025-07-24 Thu (UTC), 5 new articles found for cs.SD Sound]
toXiv_bot_toot

Breakdown of the thermodynamic limit in quantum spin and dimer models
Jeet Shah, Laura Shou, Jeremy Shuler, Victor Galitski
https://arxiv.org/abs/2506.15769

Breakdown of the thermodynamic limit in quantum spin and dimer models
The thermodynamic limit is foundational to statistical mechanics, underlying our understanding of many-body phases. It assumes that, as the system size grows infinitely at fixed density of particles, unambiguous macroscopic phases emerge that are independent of the system's boundary shape. We present explicit quantum spin and dimer Hamiltonians whose ground states violate this principle. Our construction relies on the previous mathematical work on classical dimers on the Aztec diamond and the s…

Replaced article(s) found for cs.SD. https://arxiv.org/list/cs.SD/new
[1/1]:
- Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Gui...
Hussain, Neekhara, Yang, Casanova, Ghosh, Desta, Fejgin, Valle, Li

Two Types of Temporal Symmetry in the Laws of Nature
A. Y. Klimenko
https://arxiv.org/abs/2506.15730 https://arxiv.org/pdf/2506.15730…

Two Types of Temporal Symmetry in the Laws of Nature
This work explores the implications of assuming time symmetry and applying bridge-type, time-symmetric temporal boundary conditions to deterministic laws of nature with random components. The analysis, drawing on the works of Kolmogorov and Anderson, leads to two forms of governing equations, referred to here as symmetric and antisymmetric. These equations account for the emergence of characteristics associated with conventional thermodynamics, the arrow of time, and a form of antecedent causal…

Universal Music Representations? Evaluating Foundation Models on World Music Corpora
Charilaos Papaioannou, Emmanouil Benetos, Alexandros Potamianos
https://arxiv.org/abs/2506.17055

Universal Music Representations? Evaluating Foundation Models on World Music Corpora
Foundation models have revolutionized music information retrieval, but questions remain about their ability to generalize across diverse musical traditions. This paper presents a comprehensive evaluation of five state-of-the-art audio foundation models across six musical corpora spanning Western popular, Greek, Turkish, and Indian classical traditions. We employ three complementary methodologies to investigate these models' cross-cultural capabilities: probing to assess inherent representations…

Thermodynamics and Legendre Duality in Optimal Networks
Amilcare Porporato, Shashank Kumar Anand, Salvatore Calabrese, Luca Ridolfi, Lamberto Rondoni
https://arxiv.org/abs/2506.15727

Thermodynamics and Legendre Duality in Optimal Networks
Optimality principles in nonequilibrium transport networks are linked to a thermodynamic formalism based on generalized transport potentials endowed with Legendre duality and related contact structure. This allows quantifying the distance from non-equilibrium operating points, analogously to thermodynamic availability as well as to shed light on optimality principles in relation to different imposed constraints. Extremizations of generalized dissipation and entropy production appear as special …

ITO-Master: Inference-Time Optimization for Audio Effects Modeling of Music Mastering Processors
Junghyun Koo, Marco A. Martinez-Ramirez, Wei-Hsiang Liao, Giorgio Fabbro, Michele Mancusi, Yuki Mitsufuji
https://arxiv.org/abs/2506.16889

ITO-Master: Inference-Time Optimization for Audio Effects Modeling of Music Mastering Processors
Music mastering style transfer aims to model and apply the mastering characteristics of a reference track to a target track, simulating the professional mastering process. However, existing methods apply fixed processing based on a reference track, limiting users' ability to fine-tune the results to match their artistic intent. In this paper, we introduce the ITO-Master framework, a reference-based mastering style transfer system that integrates Inference-Time Optimization (ITO) to enable finer…

[2025-06-23 Mon (UTC), 18 new articles found for cond-mat.stat-mech Statistical Mechanics]
toXiv_bot_toot

Hybrid-Sep: Language-queried audio source separation via pre-trained Model Fusion and Adversarial Diffusion Training
Jianyuan Feng, Guangzheng Li, Yangfei Xu
https://arxiv.org/abs/2506.16833

Hybrid-Sep: Language-queried audio source separation via pre-trained Model Fusion and Adversarial Diffusion Training
Language-queried Audio Separation (LASS) employs linguistic queries to isolate target sounds based on semantic descriptions. However, existing methods face challenges in aligning complex auditory features with linguistic context while preserving separation precision. Current research efforts focus primarily on text description augmentation and architectural innovations, yet the potential of integrating pre-trained self-supervised learning (SSL) audio models and Contrastive Language-Audio Pretra…

Replaced article(s) found for cond-mat.stat-mech. https://arxiv.org/list/cond-mat.stat-mech/new
[1/1]:
- Lectures on Statistical Mechanics
Allan N. Kaufman, Bruce I. Cohen, Alain J. Brizard

Learning Magnitude Distribution of Sound Fields via Conditioned Autoencoder
Shoichi Koyama, Kenji Ishizuka
https://arxiv.org/abs/2506.16729 https://…

Learning Magnitude Distribution of Sound Fields via Conditioned Autoencoder
A learning-based method for estimating the magnitude distribution of sound fields from spatially sparse measurements is proposed. Estimating the magnitude distribution of acoustic transfer function (ATF) is useful when phase measurements are unreliable or inaccessible and has a wide range of applications related to spatial audio. We propose a neural-network-based method for the ATF magnitude estimation. The key feature of our network architecture is the input and output layers conditioned on so…

Towards Bitrate-Efficient and Noise-Robust Speech Coding with Variable Bitrate RVQ
Yunkee Chae, Kyogu Lee
https://arxiv.org/abs/2506.16538 https://

Towards Bitrate-Efficient and Noise-Robust Speech Coding with Variable Bitrate RVQ
Residual Vector Quantization (RVQ) has become a dominant approach in neural speech and audio coding, providing high-fidelity compression. However, speech coding presents additional challenges due to real-world noise, which degrades compression efficiency. Standard codecs allocate bits uniformly, wasting bitrate on noise components that do not contribute to intelligibility. This paper introduces a Variable Bitrate RVQ (VRVQ) framework for noise-robust speech coding, dynamically adjusting bitrate…

Nonequilibrium orders in parametrically driven field theories
Carl Philipp Zelle, Romain Daviet, Andrew J. Millis, Sebastian Diehl
https://arxiv.org/abs/2506.18622

Nonequilibrium orders in parametrically driven field theories
Driving quantum materials with coherent light has proven a powerful platform to realize a plethora of interesting phases and transitions, ranging from ferroelectricity to superconductivity and limit cycles in pumped magnonics. In this paper we develop the field theoretical framework to describe nonequilibrium phases that emerge in systems pumped by rapid parametric drives. We consider paradigmatic O(N) models that describe the long-wavelength fluctuations of ordering fields in many condensed ma…

AeroGPT: Leveraging Large-Scale Audio Model for Aero-Engine Bearing Fault Diagnosis
Jiale Liu, Dandan Peng, Huan Wang, Chenyu Liu, Yan-Fu Li, Min Xie
https://arxiv.org/abs/2506.16225

AeroGPT: Leveraging Large-Scale Audio Model for Aero-Engine Bearing Fault Diagnosis
Aerospace engines, as critical components in aviation and aerospace industries, require continuous and accurate fault diagnosis to ensure operational safety and prevent catastrophic failures. While deep learning techniques have been extensively studied in this context, they output logits or confidence scores, necessitating post-processing to derive actionable insights. Furthermore, the potential of large-scale audio models in this domain remains largely untapped. To address these limitations, t…

Stability of universal properties against perturbations of the Markov Chain Monte Carlo algorithm
Matteo Bacci, Claudio Bonati
https://arxiv.org/abs/2506.18561

Stability of universal properties against perturbations of the Markov Chain Monte Carlo algorithm
We numerically investigate the stability of universal properties at continuous phase transitions against perturbations of the Markov Chain Monte Carlo algorithm used to simulate the system. We consider the three dimensional XY model as test bed, and both local (single site Metropolis) and global (single cluster) updates, introducing deterministic truncation-like perturbations and stochastic perturbations in the acceptance probabilities. In (almost) all the cases we find a remarkable stability o…

Improved Intelligibility of Dysarthric Speech using Conditional Flow Matching
Shoutrik Das, Nishant Singh, Arjun Gangwar, S Umesh
https://arxiv.org/abs/2506.16127

Improved Intelligibility of Dysarthric Speech using Conditional Flow Matching
Dysarthria is a neurological disorder that significantly impairs speech intelligibility, often rendering affected individuals unable to communicate effectively. This necessitates the development of robust dysarthric-to-regular speech conversion techniques. In this work, we investigate the utility and limitations of self-supervised learning (SSL) features and their quantized representations as an alternative to mel-spectrograms for speech generation. Additionally, we explore methods to mitigate …

Two dimensional Coulomb gas in a non-conservative trap
David S. Dean, Rashed Aljasmi, Satya N. Majumdar
https://arxiv.org/abs/2506.18551 https://

Two dimensional Coulomb gas in a non-conservative trap
We study the nonequilibrium steady state of a two dimensional Coulomb gas under the action of an anisotropic harmonic trapping potential along with a non-conservative rotational force. In the case without rotation, the equilibrium (zero temperature) steady state has a uniform density supported over a a static elliptical droplet. The addition of a rotational force drives the system into a nonequilibrium steady state where the density is still uniform inside an ellipse, but the ellipse gets tilte…

VS-Singer: Vision-Guided Stereo Singing Voice Synthesis with Consistency Schr\"odinger Bridge
Zijing Zhao, Kai Wang, Hao Huang, Ying Hu, Liang He, Jichen Yang
https://arxiv.org/abs/2506.16020

VS-Singer: Vision-Guided Stereo Singing Voice Synthesis with Consistency Schrödinger Bridge
To explore the potential advantages of utilizing spatial cues from images for generating stereo singing voices with room reverberation, we introduce VS-Singer, a vision-guided model designed to produce stereo singing voices with room reverberation from scene images. VS-Singer comprises three modules: firstly, a modal interaction network integrates spatial features into text encoding to create a linguistic representation enriched with spatial information. Secondly, the decoder employs a consiste…

An Extended Model of Fractional-Dimensional Space for Anisotropic Solids with Deformed Derivatives
Jos\'e Weberszpil
https://arxiv.org/abs/2506.18127 h…

An Extended Model of Fractional-Dimensional Space for Anisotropic Solids with Deformed Derivatives
In this work, we extend a fractional-dimensional space model for anisotropic solids by incorporating a q-deformed derivative operator, inspired by Tsallis' nonadditive entropy framework. This generalization provides an analytical framework for exploring anisotropic thermal properties, within a unified and flexible mathematical formalism. We derive modified expressions for the phonon density of states and specific heat capacity, highlighting the impact of the deformation parameters on thermodyna…

Sonic4D: Spatial Audio Generation for Immersive 4D Scene Exploration
Siyi Xie, Hanxin Zhu, Tianyu He, Xin Li, Zhibo Chen
https://arxiv.org/abs/2506.15759 h…

Sonic4D: Spatial Audio Generation for Immersive 4D Scene Exploration
Recent advancements in 4D generation have demonstrated its remarkable capability in synthesizing photorealistic renderings of dynamic 3D scenes. However, despite achieving impressive visual performance, almost all existing methods overlook the generation of spatial audio aligned with the corresponding 4D scenes, posing a significant limitation to truly immersive audiovisual experiences. To mitigate this issue, we propose Sonic4D, a novel framework that enables spatial audio generation for immer…

Non-algebraic first return probability of a stretched random walk near a convex boundary and its effect on adsorption
Daniil Fedotov, Sergei Nechaev
https://arxiv.org/abs/2506.17829

Non-algebraic first return probability of a stretched random walk near a convex boundary and its effect on adsorption
The $N$-step random walk, stretched in the vicinity of a disc (in 2D) or a sphere (in 3D) of radius $R$, demonstrates a non-algebraic stretched exponential decay $P_N\sim \exp\left(-{\rm const}\, N^{1/3}\right)$ for the first return probability $P_N$ in the double-scaling limit $N=\frac{L}{a}\gg 1, \frac{R}{a}\gg 1$ conditioned that $\frac{L}{R}=c={\rm const}$. Stretching means that the length of the walk, $L=Na$ (where $a$ is the unit step length) satisfies the condition $L = cR$, where $c > Ï…

Explainable speech emotion recognition through attentive pooling: insights from attention-based temporal localization
Tahitoa Leygue (DIASI), Astrid Sabourin (DIASI), Christian Bolzmacher (DIASI), Sylvain Bouchigny (DIASI), Margarita Anastassova (DIASI), Quoc-Cuong Pham (DIASI)
https://arxiv.org/abs/2506.15754

Explainable speech emotion recognition through attentive pooling: insights from attention-based temporal localization
State-of-the-art transformer models for Speech Emotion Recognition (SER) rely on temporal feature aggregation, yet advanced pooling methods remain underexplored. We systematically benchmark pooling strategies, including Multi-Query Multi-Head Attentive Statistics Pooling, which achieves a 3.5 percentage point macro F1 gain over average pooling. Attention analysis shows 15 percent of frames capture 80 percent of emotion cues, revealing a localized pattern of emotional information. Analysis of hi…

Wealth Thermalization Hypothesis
Klaus M. Frahm, Dima L. Shepelyansky
https://arxiv.org/abs/2506.17720 https://arxiv.org/pdf/2506.177…

Wealth Thermalization Hypothesis
We introduce the wealth thermalization hypothesis according to which the wealth shared in a country or the whole world is described by the Rayleigh-Jeans thermal distribution with two conserved quantities of system wealth and norm or number of agents. This distribution depends on a dimensional parameter being the ratio of system total wealth and its dispersion range determined by highest revenues. At relatively small values of this ratio there is a formation of the Rayleigh-Jeans condensate, we…

[2025-06-23 Mon (UTC), 10 new articles found for cs.SD Sound]
toXiv_bot_toot

The free propagator of strongly anisotropic systems with free surfaces
M. A. Shpot
https://arxiv.org/abs/2506.17595 https://arxiv.org…

The free propagator of strongly anisotropic systems with free surfaces
A brief overview of fluctuation-induced forces in statistical systems with film geometry at the critical point and the calculation of Casimir amplitudes, which characterize these forces quantitatively, is presented. Particular attention is paid to the special features of strongly anisotropic $m$-axis systems at the Lifshitz point, specifically, in the case of a "$perpendicular$" orientation of surfaces with free boundary conditions. Beyond the simplest one-loop approximation, calculations of Ca…

Replaced article(s) found for cs.SD. https://arxiv.org/list/cs.SD/new
[1/1]:
- Vocoder-Free Non-Parallel Conversion of Whispered Speech With Masked Cycle-Consistent Generative ...
Dominik Wagner, Ilja Baumann, Tobias Bocklet

Finite time path field theory and a new type of universal quantum spin chain quench behaviour
Domagoj Kui\'c, Alemka Knapp, Diana \v{S}aponja-Milutinovi\'c
https://arxiv.org/abs/2506.17402

Finite time path field theory and a new type of universal quantum spin chain quench behaviour
We discuss different quench protocols for Ising and XY spin chains in a transverse magnetic field. With a sudden local magnetic field quench as a starting point, we generalize our approach to a large class of local non-sudden quenches. Using finite time path field theory perturbative methods, we show that the difference between the sudden quench and a class of quenches with non-sudden switching on the perturbation vanishes exponentially with time, apart from non-substantial modifications that a…

USAD: Universal Speech and Audio Representation via Distillation
Heng-Jui Chang, Saurabhchand Bhati, James Glass, Alexander H. Liu
https://arxiv.org/abs/2506.18843

USAD: Universal Speech and Audio Representation via Distillation
Self-supervised learning (SSL) has revolutionized audio representations, yet models often remain domain-specific, focusing on either speech or non-speech tasks. In this work, we present Universal Speech and Audio Distillation (USAD), a unified approach to audio representation learning that integrates diverse audio types - speech, sound, and music - into a single model. USAD employs efficient layer-to-layer distillation from domain-specific SSL models to train a student on a comprehensive audio …

[2025-06-24 Tue (UTC), 8 new articles found for cond-mat.stat-mech Statistical Mechanics]
toXiv_bot_toot

MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners
Fang-Duo Tsai, Shih-Lun Wu, Weijaw Lee, Sheng-Ping Yang, Bo-Rui Chen, Hao-Chung Cheng, Yi-Hsuan Yang
https://arxiv.org/abs/2506.18729

MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners
We propose MuseControlLite, a lightweight mechanism designed to fine-tune text-to-music generation models for precise conditioning using various time-varying musical attributes and reference audio signals. The key finding is that positional embeddings, which have been seldom used by text-to-music generation models in the conditioner for text conditions, are critical when the condition of interest is a function of time. Using melody control as an example, our experiments show that simply adding …

Frequency-Weighted Training Losses for Phoneme-Level DNN-based Speech Enhancement
Nasser-Eddine Monir, Paul Magron, Romain Serizel
https://arxiv.org/abs/2506.18714

Frequency-Weighted Training Losses for Phoneme-Level DNN-based Speech Enhancement
Recent advances in deep learning have significantly improved multichannel speech enhancement algorithms, yet conventional training loss functions such as the scale-invariant signal-to-distortion ratio (SDR) may fail to preserve fine-grained spectral cues essential for phoneme intelligibility. In this work, we propose perceptually-informed variants of the SDR loss, formulated in the time-frequency domain and modulated by frequency-dependent weighting schemes. These weights are designed to emphas…

Evaluating Multichannel Speech Enhancement Algorithms at the Phoneme Scale Across Genders
Nasser-Eddine Monir, Paul Magron, Romain Serizel
https://arxiv.org/abs/2506.18691

Evaluating Multichannel Speech Enhancement Algorithms at the Phoneme Scale Across Genders
Multichannel speech enhancement algorithms are essential for improving the intelligibility of speech signals in noisy environments. These algorithms are usually evaluated at the utterance level, but this approach overlooks the disparities in acoustic characteristics that are observed in different phoneme categories and between male and female speakers. In this paper, we investigate the impact of gender and phonetic content on speech enhancement algorithms. We motivate this approach by outlining…

TCDiff : An End-to-end Trajectory-Controllable Diffusion Model for Harmonious Music-Driven Group Choreography
Yuqin Dai, Wanlu Zhu, Ronghui Li, Xiu Li, Zhenyu Zhang, Jun Li, Jian Yang
https://arxiv.org/abs/2506.18671

TCDiff++: An End-to-end Trajectory-Controllable Diffusion Model for Harmonious Music-Driven Group Choreography
Music-driven dance generation has garnered significant attention due to its wide range of industrial applications, particularly in the creation of group choreography. During the group dance generation process, however, most existing methods still face three primary issues: multi-dancer collisions, single-dancer foot sliding and abrupt swapping in the generation of long group dance. In this paper, we propose TCDiff++, a music-driven end-to-end framework designed to generate harmonious group danc…

Smooth Operators: LLMs Translating Imperfect Hints into Disfluency-Rich Transcripts
Duygu Altinok
https://arxiv.org/abs/2506.18510 https://

Smooth Operators: LLMs Translating Imperfect Hints into Disfluency-Rich Transcripts
Accurate detection of disfluencies in spoken language is crucial for enhancing the performance of automatic speech and language processing systems, as well as fostering the development of more inclusive speech and language technologies. Leveraging the growing trend of large language models (LLMs) as versatile learners capable of processing both lexical and non-lexical inputs (e.g., audio and video), we propose a novel approach to transcribing disfluencies as explicit tokens with timestamps, ena…

AI-Generated Song Detection via Lyrics Transcripts
Markus Frohmann, Elena V. Epure, Gabriel Meseguer-Brocal, Markus Schedl, Romain Hennequin
https://arxiv.org/abs/2506.18488

AI-Generated Song Detection via Lyrics Transcripts
The recent rise in capabilities of AI-based music generation tools has created an upheaval in the music industry, necessitating the creation of accurate methods to detect such AI-generated content. This can be done using audio-based detectors; however, it has been shown that they struggle to generalize to unseen generators or when the audio is perturbed. Furthermore, recent work used accurate and cleanly formatted lyrics sourced from a lyrics provider database to detect AI-generated music. Howe…

Selecting N-lowest scores for training MOS prediction models
Yuto Kondo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko
https://arxiv.org/abs/2506.18326 htt…

Selecting N-lowest scores for training MOS prediction models
The automatic speech quality assessment (SQA) has been extensively studied to predict the speech quality without time-consuming questionnaires. Recently, neural-based SQA models have been actively developed for speech samples produced by text-to-speech or voice conversion, with a primary focus on training mean opinion score (MOS) prediction models. The quality of each speech sample may not be consistent across the entire duration, and it remains unclear which segments of the speech receive the …

Large-Scale Training Data Attribution for Music Generative Models via Unlearning
Woosung Choi, Junghyun Koo, Kin Wai Cheuk, Joan Serr\`a, Marco A. Mart\'inez-Ram\'irez, Yukara Ikemiya, Naoki Murata, Yuhta Takida, Wei-Hsiang Liao, Yuki Mitsufuji
https://arxiv.org/abs/2506.18312

Large-Scale Training Data Attribution for Music Generative Models via Unlearning
This paper explores the use of unlearning methods for training data attribution (TDA) in music generative models trained on large-scale datasets. TDA aims to identify which specific training data points contributed to the generation of a particular output from a specific model. This is crucial in the context of AI-generated music, where proper recognition and credit for original artists are generally overlooked. By enabling white-box attribution, our work supports a fairer system for acknowledg…

Rethinking Mean Opinion Scores in Speech Quality Assessment: Aggregation through Quantized Distribution Fitting
Yuto Kondo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko
https://arxiv.org/abs/2506.18307

Rethinking Mean Opinion Scores in Speech Quality Assessment: Aggregation through Quantized Distribution Fitting
Speech quality assessment (SQA) aims to evaluate the quality of speech samples without relying on time-consuming listener questionnaires. Recent efforts have focused on training neural-based SQA models to predict the mean opinion score (MOS) of speech samples produced by text-to-speech or voice conversion systems. This paper targets the enhancement of MOS prediction models' performance. We propose a novel score aggregation method to address the limitations of conventional annotations for MOS, w…

JIS: A Speech Corpus of Japanese Idol Speakers with Various Speaking Styles
Yuto Kondo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko
https://arxiv.org/abs/2506.18296

JIS: A Speech Corpus of Japanese Idol Speakers with Various Speaking Styles
We construct Japanese Idol Speech Corpus (JIS) to advance research in speech generation AI, including text-to-speech synthesis (TTS) and voice conversion (VC). JIS will facilitate more rigorous evaluations of speaker similarity in TTS and VC systems since all speakers in JIS belong to a highly specific category: "young female live idols" in Japan, and each speaker is identified by a stage name, enabling researchers to recruit listeners familiar with these idols for listening experiments. With i…

Human Voice is Unique
Rita Singh, Bhiksha Raj
https://arxiv.org/abs/2506.18182 https://arxiv.org/pdf/2506.18182

Human Voice is Unique
Voice is increasingly being used as a biometric entity in many applications. These range from speaker identification and verification systems to human profiling technologies that attempt to estimate myriad aspects of the speaker's persona from their voice. However, for an entity to be a true biometric identifier, it must be unique. This paper establishes a first framework for calculating the uniqueness of human voice objectively. The approach in this paper is based on statistical considerations…

GD-Retriever: Controllable Generative Text-Music Retrieval with Diffusion Models
Julien Guinot, Elio Quinton, Gy\"orgy Fazekas
https://arxiv.org/abs/2506.17886

GD-Retriever: Controllable Generative Text-Music Retrieval with Diffusion Models
Multimodal contrastive models have achieved strong performance in text-audio retrieval and zero-shot settings, but improving joint embedding spaces remains an active research area. Less attention has been given to making these systems controllable and interactive for users. In text-music retrieval, the ambiguity of freeform language creates a many-to-many mapping, often resulting in inflexible or unsatisfying results. We introduce Generative Diffusion Retriever (GDR), a novel framework that l…

CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning
Angelos-Nikolaos Kanatas, Charilaos Papaioannou, Alexandros Potamianos
https://arxiv.org/abs/2506.17818

CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning
Recent advances in music foundation models have improved audio representation learning, yet their effectiveness across diverse musical traditions remains limited. We introduce CultureMERT-95M, a multi-culturally adapted foundation model developed to enhance cross-cultural music representation learning and understanding. To achieve this, we propose a two-stage continual pre-training strategy that integrates learning rate re-warming and re-decaying, enabling stable adaptation even with limited co…

SLAP: Siamese Language-Audio Pretraining Without Negative Samples for Music Understanding
Julien Guinot, Alain Riou, Elio Quinton, Gy\"orgy Fazekas
https://arxiv.org/abs/2506.17815

SLAP: Siamese Language-Audio Pretraining Without Negative Samples for Music Understanding
Joint embedding spaces have significantly advanced music understanding and generation by linking text and audio through multimodal contrastive learning. However, these approaches face large memory requirement limitations due to relying on large batch sizes to effectively utilize negative samples. Further, multimodal joint embedding spaces suffer from a modality gap wherein embeddings from different modalities lie in different manifolds of the embedding space. To address these challenges, we pro…

Algebraic Structures in Microtonal Music
Veronica Flynn, Carmen Rovi
https://arxiv.org/abs/2506.17778 https://arxiv.org/pdf/2506.1777…

Algebraic Structures in Microtonal Music
We will discuss how certain group theory structures are found in music theory. Western music splits the octave into 12 equal tones called half-steps. We can take this division further and split the octave into 24 equal tones by splitting each half-step in two, called a quarter-step. By assigning each of these 24 notes a number, we can discuss musical actions mathematically. In this paper, we analyze 24-tone microtonal music and explore how musical and harmonic structures in this system can be i…

From Generality to Mastery: Composer-Style Symbolic Music Generation via Large-Scale Pre-training
Mingyang Yao, Ke Chen
https://arxiv.org/abs/2506.17497 ht…

From Generality to Mastery: Composer-Style Symbolic Music Generation via Large-Scale Pre-training
Despite progress in controllable symbolic music generation, data scarcity remains a challenge for certain control modalities. Composer-style music generation is a prime example, as only a few pieces per composer are available, limiting the modeling of both styles and fundamental music elements (e.g., melody, chord, rhythm). In this paper, we investigate how general music knowledge learned from a broad corpus can enhance the mastery of specific composer styles, with a focus on piano piece genera…

Adaptive Control Attention Network for Underwater Acoustic Localization and Domain Adaptation
Quoc Thinh Vo, Joe Woods, Priontu Chowdhury, David K. Han
https://arxiv.org/abs/2506.17409

Adaptive Control Attention Network for Underwater Acoustic Localization and Domain Adaptation
Localizing acoustic sound sources in the ocean is a challenging task due to the complex and dynamic nature of the environment. Factors such as high background noise, irregular underwater geometries, and varying acoustic properties make accurate localization difficult. To address these obstacles, we propose a multi-branch network architecture designed to accurately predict the distance between a moving acoustic source and a receiver, tested on real-world underwater signal arrays. The network lev…

Zero-Shot Cognitive Impairment Detection from Speech Using AudioLLM
Mostafa Shahin, Beena Ahmed, Julien Epps
https://arxiv.org/abs/2506.17351 https://

Zero-Shot Cognitive Impairment Detection from Speech Using AudioLLM
Cognitive impairment (CI) is of growing public health concern, and early detection is vital for effective intervention. Speech has gained attention as a non-invasive and easily collectible biomarker for assessing cognitive decline. Traditional CI detection methods typically rely on supervised models trained on acoustic and linguistic features extracted from speech, which often require manual annotation and may not generalise well across datasets and languages. In this work, we propose the first…

[2025-06-24 Tue (UTC), 19 new articles found for cs.SD Sound]
toXiv_bot_toot

Replaced article(s) found for cs.SD. https://arxiv.org/list/cs.SD/new
[1/1]:
- TAPS: Throat and Acoustic Paired Speech Dataset for Deep Learning-Based Speech Enhancement
Yunsik Kim, Yonghun Song, Yoonyoung Chung