Tootfinder

Improving Contextual ASR via Multi-grained Fusion with Large Language Models
Shilin Zhou, Zhenghua Li
https://arxiv.org/abs/2507.12252 https://

Improving Contextual ASR via Multi-grained Fusion with Large Language Models
While end-to-end Automatic Speech Recognition (ASR) models have shown impressive performance in transcribing general speech, they often struggle to accurately recognize contextually relevant keywords, such as proper nouns or user-specific entities. Previous approaches have explored leveraging keyword dictionaries in the textual modality to improve keyword recognition, either through token-level fusion that guides token-by-token generation or phrase-level fusion that enables direct copying of …

Unifying Streaming and Non-streaming Zipformer-based ASR
Bidisha Sharma, Karthik Pandia Durai, Shankar Venkatesan, Jeena J Prakash, Shashi Kumar, Malolan Chetlur, Andreas Stolcke
https://arxiv.org/abs/2506.14434

Unifying Streaming and Non-streaming Zipformer-based ASR
There has been increasing interest in unifying streaming and non-streaming automatic speech recognition (ASR) models to reduce development, training, and deployment costs. We present a unified framework that trains a single end-to-end ASR model for both streaming and non-streaming applications, leveraging future context information. We propose to use dynamic right-context through the chunked attention masking in the training of zipformer-based ASR models. We demonstrate that using right-context…

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 …

CLIP the Landscape: Automated Tagging of Crowdsourced Landscape Images
Ilya Ilyankou, Natchapon Jongwiriyanurak, Tao Cheng, James Haworth
https://arxiv.org/abs/2506.12214

CLIP the Landscape: Automated Tagging of Crowdsourced Landscape Images
We present a CLIP-based, multi-modal, multi-label classifier for predicting geographical context tags from landscape photos in the Geograph dataset--a crowdsourced image archive spanning the British Isles, including remote regions lacking POIs and street-level imagery. Our approach addresses a Kaggle competition\footnote{https://www.kaggle.com/competitions/predict-geographic-context-from-landscape-photos} task based on a subset of Geograph's 8M images, with strict evaluation: exact match accura…

Which graph motif parameters count?
Markus Bl\"aser, Radu Curticapean, Julian D\"orfler, Christian Ikenmeyer
https://arxiv.org/abs/2507.12244 htt…

Which graph motif parameters count?
For a fixed graph H, the function #IndSub(H,*) maps graphs G to the count of induced H-copies in G; this function obviously "counts something" in that it has a combinatorial interpretation. Linear combinations of such functions are called graph motif parameters and have recently received significant attention in counting complexity after a seminal paper by Curticapean, Dell and Marx (STOC'17). We show that, among linear combinations of functions #IndSub(H,*) involving only graphs H without isol…

Exploring Discrete Factor Analysis with the discFA Package in R
Reza Arabi Belaghi, Yasin Asar, Rolf Larsson
https://arxiv.org/abs/2506.13309 https://

Exploring Discrete Factor Analysis with the discFA Package in R
Literature suggested that using the traditional factor analysis for the count data may be inappropriate. With that in mind, discrete factor analysis builds on fitting systems of dependent discrete random variables to data. The data should be in the form of non-negative counts. Data may also be truncated at some positive integer value. The discFA package in R allows for two distributions: Poisson and Negative Binomial, in combination with possible zero inflation and possible truncation, hence, e…

Revisiting $\Lambda$CDM extensions in light of re-analyzed CMB data
Jacobo Asorey, Javier de Cruz P\'erez
https://arxiv.org/abs/2506.13537 https://

Revisiting $Λ$CDM extensions in light of re-analyzed CMB data
In the last years with the increasing precision in cosmological observations we have been able to establish an standard model of cosmology, the so-called $Λ$CDM, but also find some tensions between cosmological probes that are difficult to explain within the context of this model. We tested several phenomenological extensions of the $Λ$CDM with the newest datasets from the chain CMB+BAO+SNIa, to see whether they are able to alleviate the aforementioned tensions. We find that when the updated …

Robotic System for Chemical Experiment Automation with Dual Demonstration of End-effector and Jig Operations
Hikaru Sasaki, Naoto Komeno, Takumi Hachimine, Kei Takahashi, Yu-ya Ohnishi, Tetsunori Sugawara, Araki Wakiuchi, Miho Hatanaka, Tomoyuki Miyao, Hiroharu Ajiro, Mikiya Fujii, Takamitsu Matsubara
https://arxiv.org/abs/2506.…

Robotic System for Chemical Experiment Automation with Dual Demonstration of End-effector and Jig Operations
While robotic automation has demonstrated remarkable performance, such as executing hundreds of experiments continuously over several days, it is challenging to design a program that synchronizes the robot's movements with the experimental jigs to conduct an experiment. We propose a concept that enables the automation of experiments by utilizing dual demonstrations of robot motions and jig operations by chemists in an experimental environment constructed to be controlled by a robot. To verify t…

$\mathrm{^{117m}Sn}$ and $\mathrm{^{119m}Te}$ Production via Proton Bombardment on Natural Antimony and Implications for Modeling Charged Particle Reactions
Catherine E. Apgar, Andrew S. Voyles, Jon C. Batchelder, Cathy S. Cutler, Morgan B. Fox, Yun-Hsuan Lee, Dmitri G. Medvedev, Jonathan T. Morrell, Ellen M. O'Brien, Michael Skulski, C. Etienne Vermeulen, Lee A. Bernstein

$\mathrm{^{117m}Sn}$ and $\mathrm{^{119m}Te}$ Production via Proton Bombardment on Natural Antimony and Implications for Modeling Charged Particle Reactions
$\mathrm{^{117m}Sn}$ and $\mathrm{^{119}Sb}$, the latter of which is produced via a $\mathrm{^{119m}Te}$ generator, are promising radionuclides for the targeted treatment of both osteoarthritis and small mass tumors via Auger therapy. Experiments were conducted at Lawrence Berkeley National Laboratory, Los Alamos National Laboratory, and Brookhaven National Laboratory to measure the $\mathrm{^{nat}Sb}$(p,x)$\mathrm{^{117m}Sn}$ and $\mathrm{^{nat}Sb}$(p,x)$\mathrm{^{119m}Te}$ cross sections for …

PMF-CEC: Phoneme-augmented Multimodal Fusion for Context-aware ASR Error Correction with Error-specific Selective Decoding
Jiajun He, Tomoki Toda
https://arxiv.org/abs/2506.11064 …

PMF-CEC: Phoneme-augmented Multimodal Fusion for Context-aware ASR Error Correction with Error-specific Selective Decoding
End-to-end automatic speech recognition (ASR) models often struggle to accurately recognize rare words. Previously, we introduced an ASR postprocessing method called error detection and context-aware error correction (ED-CEC), which leverages contextual information such as named entities and technical terms to improve the accuracy of ASR transcripts. Although ED-CEC achieves a notable success in correcting rare words, its accuracy remains low when dealing with rare words that have similar pronu…