English
Related papers

Related papers: Bayesian Low-Rank Factorization for Robust Model A…

200 papers

Speech models have long been known to overfit individual speakers for many classification tasks. This leads to poor generalization in settings where the speakers are out-of-domain or out-of-distribution, as is common in production…

Computation and Language · Computer Science 2024-11-08 Maximillian Chen , Zhou Yu

General-purpose ASR underperforms for atypical speakers, such as L2 learners, reinforcing bias and limiting use in education and accessibility. Using the CEFR-graded Speak and Improve corpus, we show that naive fine-tuning of Whisper…

Sound · Computer Science 2025-10-14 Ling Sun , Charlotte Zhu , Shuju Shi

Recent progress in Automatic Speech Recognition (ASR) has been coupled with a substantial increase in the model sizes, which may now contain billions of parameters, leading to slow inferences even with adapted hardware. In this context,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-25 Hugo Malard , Salah Zaiem , Robin Algayres

Automatic speech recognition is a difficult problem in pattern recognition because several sources of variability exist in the speech input like the channel variations, the input might be clean or noisy, the speakers may have different…

Audio and Speech Processing · Electrical Eng. & Systems 2021-08-09 Rupam Ojha , C Chandra Sekhar

We study the problem of learning robust acoustic models in adverse environments, characterized by a significant mismatch between training and test conditions. This problem is of paramount importance for the deployment of speech recognition…

Sound · Computer Science 2022-06-30 Dino Oglic , Zoran Cvetkovic , Peter Sollich , Steve Renals , Bin Yu

Speech-driven facial animation is important for many applications including TV, film, video games, telecommunication and AR/VR. Recently, transformers have been shown to be extremely effective for this task. However, we identify two issues…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Jack Saunders , Vinay Namboodiri

Masked language models have revolutionized natural language processing systems in the past few years. A recently introduced generalization of masked language models called warped language models are trained to be more robust to the types of…

Computation and Language · Computer Science 2021-03-29 Mahdi Namazifar , John Malik , Li Erran Li , Gokhan Tur , Dilek Hakkani Tür

Transformer-based large-scale pre-trained models achieve great success. Fine-tuning is the standard practice for leveraging these models in downstream tasks. Among the fine-tuning methods, adapter-tuning provides a parameter-efficient…

Computation and Language · Computer Science 2025-05-16 Hyegang Son , Yonglak Son , Changhoon Kim , Young Geun Kim

Speech recognisers usually perform optimally only in a specific environment and need to be adapted to work well in another. For adaptation to a new speaker, there is often too little data for fine-tuning to be robust, and that data is…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-13 Rogier C. van Dalen , Shucong Zhang , Titouan Parcollet , Sourav Bhattacharya

Parameter-efficient fine-tuning methods like Low-Rank Adaptation (LoRA) have become essential for deploying large language models, yet their static parameter allocation remains suboptimal for inputs of varying complexity. We present…

Machine Learning · Computer Science 2026-05-05 Zongqian Li , Yixuan Su , Han Zhou , Zihao Fu , Nigel Collier

Speaker adaptation techniques provide a powerful solution to customise automatic speech recognition (ASR) systems for individual users. Practical application of unsupervised model-based speaker adaptation techniques to data intensive…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-16 Jiajun Deng , Xurong Xie , Tianzi Wang , Mingyu Cui , Boyang Xue , Zengrui Jin , Guinan Li , Shujie Hu , Xunying Liu

Parameter-efficient fine-tuning methods such as LoRA enable practical adaptation of large language models but provide no principled uncertainty estimates, leading to poorly calibrated predictions and unreliable behavior under domain shift.…

Machine Learning · Computer Science 2026-02-23 Ibne Farabi Shihab , Sanjeda Akter , Anuj Sharma

Developing speech technologies for low-resource languages has become a very active research field over the last decade. Among others, Bayesian models have shown some promising results on artificial examples but still lack of in situ…

End-to-end automatic speech recognition suffers from adaptation to unknown target domain speech despite being trained with a large amount of paired audio--text data. Recent studies estimate a linguistic bias of the model as the internal…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-16 Emiru Tsunoo , Yosuke Kashiwagi , Chaitanya Narisetty , Shinji Watanabe

Recent works have shown promising results in connecting speech encoders to large language models (LLMs) for speech recognition. However, several limitations persist, including limited fine-tuning options, a lack of mechanisms to enforce…

Machine Learning · Computer Science 2024-06-26 Van Tung Pham , Yist Lin , Tao Han , Wei Li , Jun Zhang , Lu Lu , Yuxuan Wang

Dysarthric speech recognition is a challenging task as dysarthric data is limited and its acoustics deviate significantly from normal speech. Model-based speaker adaptation is a promising method by using the limited dysarthric speech to…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-04 Disong Wang , Jianwei Yu , Xixin Wu , Lifa Sun , Xunying Liu , Helen Meng

The performance of automatic speaker verification (ASV) and anti-spoofing drops seriously under real-world domain mismatch conditions. The relaxed instance frequency-wise normalization (RFN), which normalizes the frequency components based…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-10 Jin Li , Man-Wai Mak , Johan Rohdin , Kong Aik Lee , Hynek Hermansky

Automatic speech recognition models are often adapted to improve their accuracy in a new domain. A potential drawback of model adaptation to new domains is catastrophic forgetting, where the Word Error Rate on the original domain is…

Sound · Computer Science 2022-10-10 Somshubra Majumdar , Shantanu Acharya , Vitaly Lavrukhin , Boris Ginsburg

End-to-end neural diarization models have usually relied on a multilabel-classification formulation of the speaker diarization problem. Recently, we proposed a powerset multiclass formulation that has beaten the state-of-the-art on multiple…

Sound · Computer Science 2024-09-25 Alexis Plaquet , Hervé Bredin

Adapting a neural text-to-speech (TTS) model to a target speaker typically involves fine-tuning most if not all of the parameters of a pretrained multi-speaker backbone model. However, serving hundreds of fine-tuned neural TTS models is…

Sound · Computer Science 2022-10-31 Nobuyuki Morioka , Heiga Zen , Nanxin Chen , Yu Zhang , Yifan Ding