Tootfinder

As the head of the Anti-Defamation League, Jonathan Greenblatt has done little to uphold his organization’s claims to fight antisemitism
as the “leading anti-hate organization in the world.”
Instead, he’s shored up the ADL’s role as little more than a fierce pro-Israel lobby group known for defending Israel by attacking its critics.
With no sense of irony, much of this effort manifests as defamatory speech
— at least in the everyday, if not the legal, sense
— by…

MIT Student Condemned Genocide — So ADL Chief Said She Helped Cause Boulder Attack
Jonathan Greenblatt accused commencement speakers of spreading antisemitic lies — and suggested they’re responsible for violent attacks.

Reminder that this time tomorrow (noon London time, Wednesday 21st May), it's the digital OpenUK meetup. Our topic is "digital sovereignty" which seems ... timely - and we have two great speakers. Open to everyone, hope you can make it!
Details and sign up here: https://www.meetup.com/openuk/events/306642326

Top ten bits of advice for new conference speakers.
https://peakd.com/php/@crell/advice-for-new-speakers

Minding the Politeness Gap in Cross-cultural Communication
Yuka Machino, Matthias Hofer, Max Siegel, Joshua B. Tenenbaum, Robert D. Hawkins
https://arxiv.org/abs/2506.15623

Minding the Politeness Gap in Cross-cultural Communication
Misunderstandings in cross-cultural communication often arise from subtle differences in interpretation, but it is unclear whether these differences arise from the literal meanings assigned to words or from more general pragmatic factors such as norms around politeness and brevity. In this paper, we report three experiments examining how speakers of British and American English interpret intensifiers like "quite" and "very." To better understand these cross-cultural differences, we developed a …

MEMS speakers enable full-range audio in wearables with ultrasound #xMEMS

You'll never become a NATIVE English speaker
No matter how hard you try, the years in the UK or Ireland, the effort in your accent, or the AI applications you might use to fake it
There is a language wall, made of accents, cultural references and seemingly illogical phrasal verbs and idioms, that we cannot jump
But IT DOESN'T MATTER.
90% of your interactions are probably with other non-native speakers. As long as you understand each other, you're good.

Neither British nor American: how Europeans speak their own flavour of English - The European Perspective
Learning English with Elton John

Smashing! 😻
https://smashingconf.com/freiburg-2025/speakers/matthias-ott

Matthias Ott — Freiburg in Germany, September 8–11.
Matthias is an independent user experience designer and web design engineer. He teaches interface prototyping at Muthesius University of Fine Arts and Design and runs workshops on modern web design, design engineering, and prototyping. He writes Own Your Web, a newsletter about personal websites, and blogs about design, development, CSS, the open web, and more on matthiasott.com.

Join us on June 26th in Mannheim for the Sylius meetup! We have an exciting lineup of speakers, including Max Pesch, who will share a post-mortem analysis of Brille24, Jacques Bodin-Hullin, who will dive into Sylius and automation, and Stephan Hochdörfer, who will introduce the Sylius stack.
Register here: https://www.

PHPUGMRN 03/25 (The Sylius Meetup), Thu, Jun 26, 2025, 7:00 PM | Meetup
**Agenda:** 19:00 CET - Intro 19:05 CET - Brille24 - Post Mortem, Max Pesch 19:50 CET - Break 20:00 CET - Sylius & Automation, let's dive in!, Jacques Bodin-Hullin 20:50 CE

For all online participants, find your Venueless access link in your order confirmation email or our email from June 13.
Our platform is user-friendly; navigate through the left menu bar for live streams of all four stages. There's a chat for comments and interaction next to the video streams, and you can switch to the Q&A function above the chat for questions to be read to the speakers. Have questions? Our Online Stage Hosts are here to help.
Thanks for joining us online…

Tracking of Intermittent and Moving Speakers : Dataset and Metrics
Taous Iatariene (MULTISPEECH), Alexandre Gu\'erin (MULTISPEECH), Romain Serizel (MULTISPEECH)
https://arxiv.org/abs/2506.11145

Tracking of Intermittent and Moving Speakers : Dataset and Metrics
This paper presents the problem of tracking intermittent and moving sources, i.e, sources that may change position when they are inactive. This issue is seldom explored, and most current tracking methods rely on spatial observations for track identity management. They are either based on a previous localization step, or designed to perform joint localization and tracking by predicting ordered position estimates. This raises concerns about whether such methods can maintain reliable track identit…

StreamMel: Real-Time Zero-shot Text-to-Speech via Interleaved Continuous Autoregressive Modeling
Hui Wang, Yifan Yang, Shujie Liu, Jinyu Li, Lingwei Meng, Yanqing Liu, Jiaming Zhou, Haoqin Sun, Yan Lu, Yong Qin
https://arxiv.org/abs/2506.12570

StreamMel: Real-Time Zero-shot Text-to-Speech via Interleaved Continuous Autoregressive Modeling
Recent advances in zero-shot text-to-speech (TTS) synthesis have achieved high-quality speech generation for unseen speakers, but most systems remain unsuitable for real-time applications because of their offline design. Current streaming TTS paradigms often rely on multi-stage pipelines and discrete representations, leading to increased computational cost and suboptimal system performance. In this work, we propose StreamMel, a pioneering single-stage streaming TTS framework that models continu…

For all the German speakers in my network: this wonderful and entertaining podcast by ZEIT Wissen takes my research on workplace environments and makes it personal by walking through their own offices, assessing them and checking in with staff on how they feel
The big question: which office form is best? Single offices, shared or open-plan? Assigned desks or activity based working?
Must listen! 👏🏻

Einzelbüro, Großraum, Zuhause? Wo der Mensch am besten arbeitet
ZEIT WISSEN. Woher weißt Du das? · Episode

"Rebuilding the library community in a post-Twitter world" by Ned Potter: https://www.ned-potter.com/blog/rebuilding-the-library-community-in-a-post-twitter-world
(unfortunately, due to "audience reasons" he pr…

Meet the Speakers! Join us on June 26th in Mannheim to meet our lineup of speakers, including Max Pesch, Jacques Bodin-Hullin, and Stephan Hochdörfer.
Register here: https://www.meetup.com/phpug-rhein-neckar/events/305478305/

PHPUGMRN 03/25 (The Sylius Meetup), Thu, Jun 26, 2025, 7:00 PM | Meetup
**Agenda:** 19:00 CET - Intro 19:05 CET - Brille24 - Post Mortem, Max Pesch 19:50 CET - Break 20:00 CET - Sylius & Automation, let's dive in!, Jacques Bodin-Hullin 20:50 CE

11th International Conference on Language, Literature & Culture (Batman University, Çankaya University, Prešov University, Toruń Nicolaus Copernicus University) Keynote Speakers: Prof. Hywel Dix, Bournemouth University and Prof. Adelheid Rundholz, JCSU
https://ift.tt/yAuKC08
updated: Monday, June 16, 20…

Brown is celebrating 60 years of pioneering research in planetary science. An amazing list of speakers from great scientists to great communicators (like Andrew Chaikin, Emily Lakdawalla). Free!
https://events.brown.edu/earth-environ

Brown in Orbit: 60+ Years of Planetary Sciences at Brown
Join the Department of Earth, Environmental and Planetary Sciences at Brown for a two-day symposium of the Planetary Sciences and Brown’s leaders...

This Wednesday afternoon April 9th from 3-6pm there's an end of life information event at the Westbury Community Centre.
Speakers include myself, the northern Palliative Care Tasmania coordinator and a social worker with palliative care.
There will also be a short film.
I'll be discussing rights, options, choices, and money saving tips.
#tasmania

Meine Logitec-BT-Lautsprecher mal wieder aktiviert und bisschen mitm EQ rumgetjuhnt.
„Murder“ von Faderhead boomt ganz gut. ^^

The Kuba Komet entertainment center from 1957. It had eight speakers - quite a design masterpiece for the time, and it still looks pretty damn good today
#design #50s #1950s

💡 Beim Markt der Möglichkeiten (Freitag, der 26.09.2025 10:00–12:30 Uhr) sind Marktbesucher:innen herzlich dazu eingeladen in unserer Speakers-Corner mit einer kurzen Marktrede (max. 2 Min) auf den eigenen Marktstand, eine eigene Veranstaltung oder eine gute Idee hinzuweisen.
Die Programmplanung befindet sich in den letzten Zügen und wird in Kürze veröffentlicht!
#4CultureCommunityPlenary

This https://arxiv.org/abs/2409.16613 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Oral exams in introductory statistics class with non-native English speakers
Oral exams are a powerful tool to assess student's learning. This is particularly important in introductory statistics classes where students struggle to grasp various topics like the interpretation of probability, $p$-values and more. The challenge of acquiring conceptual understanding is only heightened when students are learning in a second language. In this paper, I share my experience administering oral exams to an introductory statistics class of non-native English speakers at a Japanese …

I am seeking speakers for my @… & @… meetups. We prefer in-person presentations in Frankfurt or the Mannheim area, but remote talks are also an option.
If you have anything interesting to share with us, let us know. We'd be …

UltrasonicSpheres: Localized, Multi-Channel Sound Spheres Using Off-the-Shelf Speakers and Earables
Michael K\"uttner, Valeria Sitz, Kathrin Gerling, Michael Beigl, Tobias R\"oddiger
https://arxiv.org/abs/2506.02715

UltrasonicSpheres: Localized, Multi-Channel Sound Spheres Using Off-the-Shelf Speakers and Earables
We present a demo ofUltrasonicSpheres, a novel system for location-specific audio delivery using wearable earphones that decode ultrasonic signals into audible sound. Unlike conventional beamforming setups, UltrasonicSpheres relies on single ultrasonic speakers to broadcast localized audio with multiple channels, each encoded on a distinct ultrasonic carrier frequency. Users wearing our acoustically transparent earphones can demodulate their selected stream, such as exhibit narrations in a chos…

Stalled on getting MSFS 2024 to run, but did clean off the desk a bit. Not the best case scenario, but figured a nice lazy Saturday just relaxing would work out well.
#desktop

Last night scrolling my phone I saw an add for a CyberSecurity conference. It was localish, so I clicked. After an entire page about it only being aimed for "professionals" and specifically not "Professors and students, or sales industry professionals" (and others) which seemed unnecessary, I was unable to see the schedule or even the speakers until I registered with personal info. No thank you, I don't need to go. It just felt... icky.

For all the German speakers in my network: my research on spatial layouts and communication has been featured in a lovely and detailed article in the weekly German newspaper Die Zeit discussing the manifold relations between architecture and social outcomes, ranging from political coalition negotiations to the mutiny on the Bounty, from team meetings in offices to places for living

Architektur: Wie Architekten Gespräche lenken – und Macht verteilen
Gute Architektur verbindet Menschen, schlechte trennt sie. Wer die Gesetze des Bauens kennt, kann Politiker zusammenbringen – und sogar den Lauf der Geschichte verändern.

CMT-LLM: Contextual Multi-Talker ASR Utilizing Large Language Models
Jiajun He, Naoki Sawada, Koichi Miyazaki, Tomoki Toda
https://arxiv.org/abs/2506.12059

CMT-LLM: Contextual Multi-Talker ASR Utilizing Large Language Models
In real-world applications, automatic speech recognition (ASR) systems must handle overlapping speech from multiple speakers and recognize rare words like technical terms. Traditional methods address multi-talker ASR and contextual biasing separately, limiting performance in complex scenarios. We propose a unified framework that combines multi-talker overlapping speech recognition and contextual biasing into a single task. Our ASR method integrates pretrained speech encoders and large language …

Mitigating Non-Target Speaker Bias in Guided Speaker Embedding
Shota Horiguchi, Takanori Ashihara, Marc Delcroix, Atsushi Ando, Naohiro Tawara
https://arxiv.org/abs/2506.12500

Mitigating Non-Target Speaker Bias in Guided Speaker Embedding
Obtaining high-quality speaker embeddings in multi-speaker conditions is crucial for many applications. A recently proposed guided speaker embedding framework, which utilizes speech activities of target and non-target speakers as clues, drastically improved embeddings under severe overlap with small degradation in low-overlap cases. However, since extreme overlaps are rare in natural conversations, this degradation cannot be overlooked. This paper first reveals that the degradation is caused by…

What do you say, warring generation tribes?

Developing a Mixed-Methods Pipeline for Community-Oriented Digitization of Kwak'wala Legacy Texts
Milind Agarwal, Daisy Rosenblum, Antonios Anastasopoulos
https://arxiv.org/abs/2506.01775

Developing a Mixed-Methods Pipeline for Community-Oriented Digitization of Kwak'wala Legacy Texts
Kwak'wala is an Indigenous language spoken in British Columbia, with a rich legacy of published documentation spanning more than a century, and an active community of speakers, teachers, and learners engaged in language revitalization. Over 11 volumes of the earliest texts created during the collaboration between Franz Boas and George Hunt have been scanned but remain unreadable by machines. Complete digitization through optical character recognition has the potential to facilitate transliterat…

🚀 Kubernetes Meetup in Nuremberg! 🇩🇪
Join us on June 2nd for an evening of tech talks, networking, and community fun at the next CNCF Meetup!
🎤 Speakers:
🔹 Sarah Julia Kriesch – Docker vs Podman and the Universe
🔹 Philip Laine – Spegel: A Stateless OCI Registry Mirror
📍 Location: Coworking-Space Nürnberg
🕕 18:00: Doors open for networking
🕡 18:30: Talks begin
🔗 Sign up here:

Evaluating Logit-Based GOP Scores for Mispronunciation Detection
Aditya Kamlesh Parikh, Cristian Tejedor-Garcia, Catia Cucchiarini, Helmer Strik
https://arxiv.org/abs/2506.12067

Evaluating Logit-Based GOP Scores for Mispronunciation Detection
Pronunciation assessment relies on goodness of pronunciation (GOP) scores, traditionally derived from softmax-based posterior probabilities. However, posterior probabilities may suffer from overconfidence and poor phoneme separation, limiting their effectiveness. This study compares logit-based GOP scores with probability-based GOP scores for mispronunciation detection. We conducted our experiment on two L2 English speech datasets spoken by Dutch and Mandarin speakers, assessing classification …

This https://arxiv.org/abs/2505.20529 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSD_…

Training Articulatory Inversion Models for Inter-Speaker Consistency
Acoustic-to-Articulatory Inversion (AAI) attempts to model the inverse mapping from speech to articulation. Exact articulatory prediction from speech alone may be impossible, as speakers can choose different forms of articulation seemingly without reference to their vocal tract structure. However, once a speaker has selected an articulatory form, their productions vary minimally. Recent works in AAI have proposed adapting Self-Supervised Learning (SSL) models to single-speaker datasets, claimin…

Religious Studies Project Opportunities Digest – November 6, 2024
https://ift.tt/0Rr82c1
Welcome to the Religious Studies Project Opportunities Digest! This week, you will find 23 new job…
via Input 4 RELCFP

Religious Studies Project Opportunities Digest - November 6, 2024 | The Religious Studies Project
Welcome to the Religious Studies Project Opportunities Digest! This week, you will find 23 new job opportunities, 2 call for papers, and 2 conferences/speakers.

Improving Neural Diarization through Speaker Attribute Attractors and Local Dependency Modeling
David Palzer, Matthew Maciejewski, Eric Fosler-Lussier
https://arxiv.org/abs/2506.05593

Improving Neural Diarization through Speaker Attribute Attractors and Local Dependency Modeling
In recent years, end-to-end approaches have made notable progress in addressing the challenge of speaker diarization, which involves segmenting and identifying speakers in multi-talker recordings. One such approach, Encoder-Decoder Attractors (EDA), has been proposed to handle variable speaker counts as well as better guide the network during training. In this study, we extend the attractor paradigm by moving beyond direct speaker modeling and instead focus on representing more detailed `speake…

Religious Studies Project Opportunities Digest – October 23, 2024
https://ift.tt/yr74kin
Welcome to the Religious Studies Project Opportunities Digest! This week, you will find 13 new job…
via Input 4 RELCFP

Religious Studies Project Opportunities Digest - October 23, 2024 | The Religious Studies Project
Welcome to the Religious Studies Project Opportunities Digest! This week, you will find 13 new job opportunities, 2 fellowships, 2 call for papers, and 4 conferences/speakers.

AuralNet: Hierarchical Attention-based 3D Binaural Localization of Overlapping Speakers
Linya Fu, Yu Liu, Zhijie Liu, Zedong Yang, Zhong-Qiu Wang, Youfu Li, He Kong
https://arxiv.org/abs/2506.02773

AuralNet: Hierarchical Attention-based 3D Binaural Localization of Overlapping Speakers
We propose AuralNet, a novel 3D multi-source binaural sound source localization approach that localizes overlapping sources in both azimuth and elevation without prior knowledge of the number of sources. AuralNet employs a gated coarse-tofine architecture, combining a coarse classification stage with a fine-grained regression stage, allowing for flexible spatial resolution through sector partitioning. The model incorporates a multi-head self-attention mechanism to capture spatial cues in binaur…

Conformer-based Ultrasound-to-Speech Conversion
Ibrahim Ibrahimov, Zaink\'o Csaba, G\'abor Gosztolya
https://arxiv.org/abs/2506.03831 https://

Conformer-based Ultrasound-to-Speech Conversion
Deep neural networks have shown promising potential for ultrasound-to-speech conversion task towards Silent Speech Interfaces. In this work, we applied two Conformer-based DNN architectures (Base and one with bi-LSTM) for this task. Speaker-specific models were trained on the data of four speakers from the Ultrasuite-Tal80 dataset, while the generated mel spectrograms were synthesized to audio waveform using a HiFi-GAN vocoder. Compared to a standard 2D-CNN baseline, objective measurements (MSE…

Religious Studies Opportunities Digest – October 30, 2024
https://ift.tt/7gduRDy
Welcome to the Religious Studies Project Opportunities Digest! This week, you will find 35 new job…
via Input 4 RELCFP

Religious Studies Opportunities Digest - October 30, 2024 | The Religious Studies Project
Welcome to the Religious Studies Project Opportunities Digest! This week, you will find 35 new job opportunities, 1 fellowship, 1 grant, 8 call for papers, and 11 conferences/speakers.

You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks
\"Unal Ege Gaznepoglu, Anna Leschanowsky, Ahmad Aloradi, Prachi Singh, Daniel Tenbrinck, Emanu\"el A. P. Habets, Nils Peters
https://arxiv.org/abs/2506.09521

You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks
Speaker anonymization systems hide the identity of speakers while preserving other information such as linguistic content and emotions. To evaluate their privacy benefits, attacks in the form of automatic speaker verification (ASV) systems are employed. In this study, we assess the impact of intra-speaker linguistic content similarity in the attacker training and evaluation datasets, by adapting BERT, a language model, as an ASV system. On the VoicePrivacy Attacker Challenge datasets, our metho…

Religious Studies Project Opportunites Digest – October 16, 2024
https://ift.tt/DYXyxPU
Welcome to the Religious Studies Project Opportunities Digest! This week, you will find 38 new job…
via Input 4 RELCFP

Religious Studies Project Opportunites Digest - October 16, 2024 | The Religious Studies Project
Welcome to the Religious Studies Project Opportunities Digest! This week, you will find 38 new job opportunities, 5 fellowships, 3 grants, 5 call for papers, 12 conferences/speakers, and 1 other opportunity.

Dhvani: A Weakly-supervised Phonemic Error Detection and Personalized Feedback System for Hindi
Arnav Rustagi, Satvik Bajpai, Nimrat Kaur, Siddharth Siddharth
https://arxiv.org/abs/2506.02166

Dhvani: A Weakly-supervised Phonemic Error Detection and Personalized Feedback System for Hindi
Computer-Assisted Pronunciation Training (CAPT) has been extensively studied for English. However, there remains a critical gap in its application to Indian languages with a base of 1.5 billion speakers. Pronunciation tools tailored to Indian languages are strikingly lacking despite the fact that millions learn them every year. With over 600 million speakers and being the fourth most-spoken language worldwide, improving Hindi pronunciation is a vital first step toward addressing this gap. This …

Fine-Tuning ASR for Stuttered Speech: Personalized vs. Generalized Approaches
Dena Mujtaba, Nihar Mahapatra
https://arxiv.org/abs/2506.00853 https://

Fine-Tuning ASR for Stuttered Speech: Personalized vs. Generalized Approaches
Stuttering -- characterized by involuntary disfluencies such as blocks, prolongations, and repetitions -- is often misinterpreted by automatic speech recognition (ASR) systems, resulting in elevated word error rates and making voice-driven technologies inaccessible to people who stutter. The variability of disfluencies across speakers and contexts further complicates ASR training, compounded by limited annotated stuttered speech data. In this paper, we investigate fine-tuning ASRs for stuttered…

Religious Studies Project Opportunities Digest – November 18, 2024
https://ift.tt/xWgVf8N
Welcome to the Religious Studies Project Opportunities Digest! This week, you will find 36 new job…
via Input 4 RELCFP

Religious Studies Project Opportunities Digest - November 18, 2024 | The Religious Studies Project
Welcome to the Religious Studies Project Opportunities Digest! This week, you will find 36 new job opportunities, 12 fellowships, 1 grant, 7 calls for papers, 3 conferences/speakers, and 3 other opportunities.

Recognizing Every Voice: Towards Inclusive ASR for Rural Bhojpuri Women
Sakshi Joshi, Eldho Ittan George, Tahir Javed, Kaushal Bhogale, Nikhil Narasimhan, Mitesh M. Khapra
https://arxiv.org/abs/2506.09653

Recognizing Every Voice: Towards Inclusive ASR for Rural Bhojpuri Women
Digital inclusion remains a challenge for marginalized communities, especially rural women in low-resource language regions like Bhojpuri. Voice-based access to agricultural services, financial transactions, government schemes, and healthcare is vital for their empowerment, yet existing ASR systems for this group remain largely untested. To address this gap, we create SRUTI ,a benchmark consisting of rural Bhojpuri women speakers. Evaluation of current ASR models on SRUTI shows poor performance…

Religious Studies Project Opportunities Digest – November 13, 2024
https://ift.tt/F5L69zB
Welcome to the Religious Studies Project Opportunities Digest! This week, you will find 13 new job…
via Input 4 RELCFP

Religious Studies Project Opportunities Digest - November 13, 2024 | The Religious Studies Project
Welcome to the Religious Studies Project Opportunities Digest! This week, you will find 13 new job opportunities, 6 fellowships, 3 grants, 4 calls for papers, 4 conferences/speakers, and 1 other submission.

This https://arxiv.org/abs/2506.01483 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Inter-Speaker Relative Cues for Text-Guided Target Speech Extraction
We propose a novel approach that utilize inter-speaker relative cues for distinguishing target speakers and extracting their voices from mixtures. Continuous cues (e.g., temporal order, age, pitch level) are grouped by relative differences, while discrete cues (e.g., language, gender, emotion) retain their categories. Relative cues offers greater flexibility than fixed speech attribute classification, facilitating much easier expansion of text-guided target speech extraction datasets. Our exper…

Religious Studies Project Opportunities Digest – October 9, 2024
https://ift.tt/aHDBoXS
Welcome to the Religious Studies Project Opportunities Digest! This week, you will find 28 new job…
via Input 4 RELCFP

Religious Studies Project Opportunities Digest - October 9, 2024 | The Religious Studies Project
Welcome to the Religious Studies Project Opportunities Digest! This week, you will find 28 new job opportunities, 3 fellowships, 2 grants, 5 call for papers, and 3 conferences/speakers. Everyone at RSP says thank you to all who have generously supported the RSP through our Patreon and PayPal donation options! Our goal is to have 100 patrons (currently at 39!) […]

This https://arxiv.org/abs/2506.01483 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Inter-Speaker Relative Cues for Text-Guided Target Speech Extraction
We propose a novel approach that utilize inter-speaker relative cues for distinguishing target speakers and extracting their voices from mixtures. Continuous cues (e.g., temporal order, age, pitch level) are grouped by relative differences, while discrete cues (e.g., language, gender, emotion) retain their categories. Relative cues offers greater flexibility than fixed speech attribute classification, facilitating much easier expansion of text-guided target speech extraction datasets. Our exper…

French Listening Tests for the Assessment of Intelligibility, Quality, and Identity of Body-Conducted Speech Enhancement
Thomas Joubaud, Julien Hauret, V\'eronique Zimpfer, \'Eric Bavu
https://arxiv.org/abs/2506.04495

French Listening Tests for the Assessment of Intelligibility, Quality, and Identity of Body-Conducted Speech Enhancement
This study evaluates the Extreme Bandwidth Extension Network (EBEN) model on body-conduction sensors through listening tests. Using the Vibravox dataset, we assess intelligibility with a French Modified Rhyme Test, speech quality with a MUSHRA (MUltiple Stimuli with Hidden Reference and Anchor) protocol and speaker identity preservation with an A/B identification task. The experiments involved male and female speakers recorded with a forehead accelerometer, rigid in-ear and throat microphones. …

Inter-Speaker Relative Cues for Text-Guided Target Speech Extraction
Wang Dai, Archontis Politis, Tuomas Virtanen
https://arxiv.org/abs/2506.01483 https://…

Inter-Speaker Relative Cues for Text-Guided Target Speech Extraction
We propose a novel approach that utilize inter-speaker relative cues for distinguishing target speakers and extracting their voices from mixtures. Continuous cues (e.g., temporal order, age, pitch level) are grouped by relative differences, while discrete cues (e.g., language, gender, emotion) retain their categories. Relative cues offers greater flexibility than fixed speech attribute classification, facilitating much easier expansion of text-guided target speech extraction datasets. Our exper…

This https://arxiv.org/abs/2505.19314 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline
Target Speech Extraction (TSE) aims to isolate a target speaker's voice from a mixture of multiple speakers by leveraging speaker-specific cues, typically provided as auxiliary audio (a.k.a. cue audio). Although recent advancements in TSE have primarily employed discriminative models that offer high perceptual quality, these models often introduce unwanted artifacts, reduce naturalness, and are sensitive to discrepancies between training and testing environments. On the other hand, generative m…

Towards Temporally Explainable Dysarthric Speech Clarity Assessment
Seohyun Park, Chitralekha Gupta, Michelle Kah Yian Kwan, Xinhui Fung, Alexander Wenjun Yip, Suranga Nanayakkara
https://arxiv.org/abs/2506.00454

Towards Temporally Explainable Dysarthric Speech Clarity Assessment
Dysarthria, a motor speech disorder, affects intelligibility and requires targeted interventions for effective communication. In this work, we investigate automated mispronunciation feedback by collecting a dysarthric speech dataset from six speakers reading two passages, annotated by a speech therapist with temporal markers and mispronunciation descriptions. We design a three-stage framework for explainable mispronunciation evaluation: (1) overall clarity scoring, (2) mispronunciation localiza…

This https://arxiv.org/abs/2409.03636 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

ZSDEVC: Zero-Shot Diffusion-based Emotional Voice Conversion with Disentangled Mechanism
The human voice conveys not just words but also emotional states and individuality. Emotional voice conversion (EVC) modifies emotional expressions while preserving linguistic content and speaker identity, improving applications like human-machine interaction. While deep learning has advanced EVC models for specific target speakers on well-crafted emotional datasets, existing methods often face issues with emotion accuracy and speech distortion. In addition, the zero-shot scenario, in which emo…

Quantifying and Reducing Speaker Heterogeneity within the Common Voice Corpus for Phonetic Analysis
Miao Zhang, Aref Farhadipour, Annie Baker, Jiachen Ma, Bogdan Pricop, Eleanor Chodroff
https://arxiv.org/abs/2506.00733

Quantifying and Reducing Speaker Heterogeneity within the Common Voice Corpus for Phonetic Analysis
With its crosslinguistic and cross-speaker diversity, the Mozilla Common Voice Corpus (CV) has been a valuable resource for multilingual speech technology and holds tremendous potential for research in crosslinguistic phonetics and speech sciences. Properly accounting for speaker variation is, however, key to the theoretical and statistical bases of speech research. While CV provides a client ID as an approximation to a speaker ID, multiple speakers can contribute under the same ID. This study …