English
Related papers

Related papers: OWSM-Biasing: Contextualizing Open Whisper-Style S…

200 papers

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

In this paper, we present our initial efforts for building a code-switching (CS) speech recognition system leveraging existing acoustic models (AMs) and language models (LMs), i.e., no training required, and specifically targeting…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-03 Zhen Huang , Xiaodan Zhuang , Daben Liu , Xiaoqiang Xiao , Yuchen Zhang , Sabato Marco Siniscalchi

Learning to recognize new keywords with just a few examples is essential for personalizing keyword spotting (KWS) models to a user's choice of keywords. However, modern KWS models are typically trained on large datasets and restricted to a…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-07 Abhijeet Awasthi , Kevin Kilgour , Hassan Rom

Despite the success of deep learning in speech recognition, multi-dialect speech recognition remains a difficult problem. Although dialect-specific acoustic models are known to perform well in general, they are not easy to maintain when…

Machine Learning · Computer Science 2022-05-09 Sanghyun Yoo , Inchul Song , Yoshua Bengio

In recent years, the performance of automatic speech recognition (ASR) systems has made considerable progress. Unfortunately, for people with speech impairments, such as people treated for oral cancer (OC), ASR performance is still lagging…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-18 Hidde Folkertsma , Thomas Tienkamp , Sebastiaan de Visscher , Max Witjes , Rob van Son , Jiapan Guo , Bence Mark Halpern

Improving the representation of contextual information is key to unlocking the potential of end-to-end (E2E) automatic speech recognition (ASR). In this work, we present a novel and simple approach for training an ASR context mechanism with…

Audio and Speech Processing · Electrical Eng. & Systems 2018-10-30 Uri Alon , Golan Pundak , Tara N. Sainath

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language…

Audio and Speech Processing · Electrical Eng. & Systems 2019-02-20 Jinxi Guo , Tara N. Sainath , Ron J. Weiss

Rich sources of variability in natural speech present significant challenges to current data intensive speech recognition technologies. To model both speaker and environment level diversity, this paper proposes a novel Bayesian factorised…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-27 Jiajun Deng , Guinan Li , Xurong Xie , Zengrui Jin , Mingyu Cui , Tianzi Wang , Shujie Hu , Mengzhe Geng , Xunying Liu

Modeling the errors of a speech recognizer can help simulate errorful recognized speech data from plain text, which has proven useful for tasks like discriminative language modeling, improving robustness of NLP systems, where limited or…

Artificial Intelligence · Computer Science 2024-08-22 Prashant Serai , Peidong Wang , Eric Fosler-Lussier

Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance…

Computation and Language · Computer Science 2021-06-04 Richard Diehl Martinez , Scott Novotney , Ivan Bulyko , Ariya Rastrow , Andreas Stolcke , Ankur Gandhe

Code-switching (CS) automatic speech recognition (ASR) faces challenges due to the language confusion resulting from accents, auditory similarity, and seamless language switches. Adaptation on the pre-trained multi-lingual model has shown…

Computation and Language · Computer Science 2025-01-07 Jiahui Zhao , Hao Shi , Chenrui Cui , Tianrui Wang , Hexin Liu , Zhaoheng Ni , Lingxuan Ye , Longbiao Wang

We previously proposed contextual spelling correction (CSC) to correct the output of end-to-end (E2E) automatic speech recognition (ASR) models with contextual information such as name, place, etc. Although CSC has achieved reasonable…

Sound · Computer Science 2023-02-23 Xiaoqiang Wang , Yanqing Liu , Jinyu Li , Sheng Zhao

Goal-oriented conversational interfaces are designed to accomplish specific tasks and typically have interactions that tend to span multiple turns adhering to a pre-defined structure and a goal. However, conventional neural language models…

Computation and Language · Computer Science 2021-06-08 Ashish Shenoy , Sravan Bodapati , Katrin Kirchhoff

Compared with automatic speech recognition (ASR), the human auditory system is more adept at handling noise-adverse situations, including environmental noise and channel distortion. To mimic this adeptness, auditory models have been widely…

Computation and Language · Computer Science 2016-09-16 Peng Dai , Xue Teng , Frank Rudzicz , Ing Yann Soon

The growing prevalence of online conferences and courses presents a new challenge in improving automatic speech recognition (ASR) with enriched textual information from video slides. In contrast to rare phrase lists, the slides within…

Sound · Computer Science 2024-01-15 Fan Yu , Haoxu Wang , Xian Shi , Shiliang Zhang

Despite being trained exclusively on speech data, speech foundation models (SFMs) like Whisper have shown impressive performance in non-speech tasks such as audio classification. This is partly because speech shares some common traits with…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-17 Orchid Chetia Phukan , Swarup Ranjan Behera , Girish , Mohd Mujtaba Akhtar , Arun Balaji Buduru , Rajesh Sharma

End-to-end (E2E) automatic speech recognition (ASR) methods exhibit remarkable performance. However, since the performance of such methods is intrinsically linked to the context present in the training data, E2E-ASR methods do not perform…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-22 Yui Sudo , Muhammad Shakeel , Yosuke Fukumoto , Yifan Peng , Shinji Watanabe

How to leverage dynamic contextual information in end-to-end speech recognition has remained an active research area. Previous solutions to this problem were either designed for specialized use cases that did not generalize well to…

Large speech foundation models achieve strong performance across many domains, but they often require adaptation to handle local needs such as code-switching, where speakers mix languages within the same utterance. Direct fine-tuning of…

Computation and Language · Computer Science 2025-10-22 Enes Yavuz Ugan , Ngoc-Quan Pham , Alexander Waibel

By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words. However, for real-world voice assistants, always biasing on such personalized words…

Sound · Computer Science 2023-08-16 Tianyi Xu , Zhanheng Yang , Kaixun Huang , Pengcheng Guo , Ao Zhang , Biao Li , Changru Chen , Chao Li , Lei Xie