Tootfinder

Adaptability of ASR Models on Low-Resource Language: A Comparative Study of Whisper and Wav2Vec-BERT on Bangla
Md Sazzadul Islam Ridoy, Sumi Akter, Md. Aminur Rahman
https://arxiv.org/abs/2507.01931

Adaptability of ASR Models on Low-Resource Language: A Comparative Study of Whisper and Wav2Vec-BERT on Bangla
In recent years, neural models trained on large multilingual text and speech datasets have shown great potential for supporting low-resource languages. This study investigates the performances of two state-of-the-art Automatic Speech Recognition (ASR) models, OpenAI's Whisper (Small & Large-V2) and Facebook's Wav2Vec-BERT on Bangla, a low-resource language. We have conducted experiments using two publicly available datasets: Mozilla Common Voice-17 and OpenSLR to evaluate model performances. Th…

From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding
Xiangfeng Wang, Xiao Li, Yadong Wei, Xueyu Song, Yang Song, Xiaoqiang Xia, Fangrui Zeng, Zaiyi Chen, Liu Liu, Gu Xu, Tong Xu
https://arxiv.org/abs/2507.02790

From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding
The rapid growth of online video content, especially on short video platforms, has created a growing demand for efficient video editing techniques that can condense long-form videos into concise and engaging clips. Existing automatic editing methods predominantly rely on textual cues from ASR transcripts and end-to-end segment selection, often neglecting the rich visual context and leading to incoherent outputs. In this paper, we propose a human-inspired automatic video editing framework (HIVE)…

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…

Revisiting Noise-adaptive Transpilation in Quantum Computing: How Much Impact Does it Have?
Yuqian Huo, Jinbiao Wei, Christopher Kverne, Mayur Akewar, Janki Bhimani, Tirthak Patel
https://arxiv.org/abs/2507.01195

Revisiting Noise-adaptive Transpilation in Quantum Computing: How Much Impact Does it Have?
Transpilation, particularly noise-aware optimization, is widely regarded as essential for maximizing the performance of quantum circuits on superconducting quantum computers. The common wisdom is that each circuit should be transpiled using up-to-date noise calibration data to optimize fidelity. In this work, we revisit the necessity of frequent noise-adaptive transpilation, conducting an in-depth empirical study across five IBM 127-qubit quantum computers and 16 diverse quantum algorithms. Our…

Lepton flavor violating decay of true muonium: $\boldsymbol{(\mu^ \mu^-) \to \mu^\pm e^\mp}$
Ryotaro Minato, Akira Sato, Ryosuke Suda, Masato Yamanaka
https://arxiv.org/abs/2507.01193

Lepton flavor violating decay of true muonium: $\boldsymbol{(μ^+ μ^-) \to μ^\pm e^\mp}$
We propose a new channel for probing charged lepton flavor violation (CLFV): the decay of true muonium into a lepton pair of different flavor, $(μ^+ μ^-) \to μ^\pm e^\mp$. This purely leptonic two-body decay provides a clean experimental signature in the form of energetic, oppositely charged leptons. It is sensitive not only to photonic dipole interactions but also to four-fermion contact interactions, and is free from hadronic uncertainties in theoretical predictions. We evaluate the branch…

NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding
Vladimir Bataev, Andrei Andrusenko, Lilit Grigoryan, Aleksandr Laptev, Vitaly Lavrukhin, Boris Ginsburg
https://arxiv.org/abs/2505.22857

NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding
Statistical n-gram language models are widely used for context-biasing tasks in Automatic Speech Recognition (ASR). However, existing implementations lack computational efficiency due to poor parallelization, making context-biasing less appealing for industrial use. This work rethinks data structures for statistical n-gram language models to enable fast and parallel operations for GPU-optimized inference. Our approach, named NGPU-LM, introduces customizable greedy decoding for all major ASR mod…

Leveraging In-Context Learning for Political Bias Testing of LLMs
Patrick Haller, Jannis Vamvas, Rico Sennrich, Lena A. J\"ager
https://arxiv.org/abs/2506.22232

Leveraging In-Context Learning for Political Bias Testing of LLMs
A growing body of work has been querying LLMs with political questions to evaluate their potential biases. However, this probing method has limited stability, making comparisons between models unreliable. In this paper, we argue that LLMs need more context. We propose a new probing task, Questionnaire Modeling (QM), that uses human survey data as in-context examples. We show that QM improves the stability of question-based bias evaluation, and demonstrate that it may be used to compare instruct…

Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activation
Zhennan Lin, Kaixun Huang, Wei Ren, Linju Yang, Lei Xie
https://arxiv.org/abs/2505.23077

Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activation
Deep biasing improves automatic speech recognition (ASR) performance by incorporating contextual phrases. However, most existing methods enhance subwords in a contextual phrase as independent units, potentially compromising contextual phrase integrity, leading to accuracy reduction. In this paper, we propose an encoder-based phrase-level contextualized ASR method that leverages dynamic vocabulary prediction and activation. We introduce architectural optimizations and integrate a bias loss to ex…

NoticeLight: Embracing Socio-Technical Asymmetry through Tangible Peripheral Robotic Embodiment in Hybrid Collaboration
Marie Altmann, Kimberly Hegemann, Ali Askari, Vineetha Rallabandi, Max Pascher, Jens Gerken
https://arxiv.org/abs/2506.22125

NoticeLight: Embracing Socio-Technical Asymmetry through Tangible Peripheral Robotic Embodiment in Hybrid Collaboration
Hybrid collaboration has become a fixture in modern workplaces, yet it introduces persistent socio-technical asymmetries-especially disadvantaging remote participants, who struggle with presence disparity, reduced visibility, and limited non-verbal communication. Traditional solutions often seek to erase these asymmetries, but recent research suggests embracing them as productive design constraints. In this context, we introduce NoticeLight: a tangible, peripheral robotic embodiment designed to…

The Instrumental Background of EP/FXT
Juan Zhang, Yong Chen, Shumei Jia, Haisheng Zhao, WeiWei Cui, Tianxiang Chen, Juan Wang, Hao Wang, Jin Wang, Chengkui Li, Xiaofan Zhao, Ju Guan, Dawei Han, Jingjing Xu, Liming Song, Hua Feng, Shuangnan Zhang, Weimin Yuan
https://arxiv.org/abs/2507.00510

The Instrumental Background of EP/FXT
The in-flight instrumental background of the Follow-up X-ray Telescope (FXT) onboard Einstein Probe (EP) mission is analysed in this work by utilizing observations collected during Performance Verification phase and subsequent dedicated filter wheel closed observations. The instrumental backgrounds of the two FXT modules are consistent with each other, with an average rate of $\sim 4\times10^{-2}$\,counts/s/keV at 0.5--10\,keV for each module. The background is nearly uniformly distributed acro…