English
Related papers

Related papers: Self-regularised Minimum Latency Training for Stre…

200 papers

Recently self-supervised learning has emerged as an effective approach to improve the performance of automatic speech recognition (ASR). Under such a framework, the neural network is usually pre-trained with massive unlabeled data and then…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-16 Songjun Cao , Yueteng Kang , Yanzhe Fu , Xiaoshuo Xu , Sining Sun , Yike Zhang , Long Ma

Self-supervised learning (SSL) models have achieved considerable improvements in automatic speech recognition (ASR). In addition, ASR performance could be further improved if the model is dedicated to audio content information learning…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-08 Genshun Wan , Tan Liu , Hang Chen , Jia Pan , Cong Liu , Zhongfu Ye

Self-supervised learning via masked prediction pre-training (MPPT) has shown impressive performance on a range of speech-processing tasks. This paper proposes a method to bias self-supervised learning towards a specific task. The core idea…

Computation and Language · Computer Science 2022-11-07 Florian L. Kreyssig , Yangyang Shi , Jinxi Guo , Leda Sari , Abdelrahman Mohamed , Philip C. Woodland

Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary model APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training…

Computer Vision and Pattern Recognition · Computer Science 2025-04-23 Joya Chen , Ziyun Zeng , Yiqi Lin , Wei Li , Zejun Ma , Mike Zheng Shou

In the present paper, an attempt is made to combine Mask-CTC and the triggered attention mechanism to construct a streaming end-to-end automatic speech recognition (ASR) system that provides high performance with low latency. The triggered…

Sound · Computer Science 2021-10-22 Huaibo Zhao , Yosuke Higuchi , Tetsuji Ogawa , Tetsunori Kobayashi

Despite the feature of real-time decoding, Monotonic Multihead Attention (MMA) shows comparable performance to the state-of-the-art offline methods in machine translation and automatic speech recognition (ASR) tasks. However, the latency of…

Computation and Language · Computer Science 2021-03-29 Jaeyun Song , Hajin Shim , Eunho Yang

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with…

In this paper, we propose an online attention mechanism, known as cumulative attention (CA), for streaming Transformer-based automatic speech recognition (ASR). Inspired by monotonic chunkwise attention (MoChA) and head-synchronous…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-14 Mohan Li , Shucong Zhang , Catalin Zorila , Rama Doddipatla

Transformer-based architectures are the most used architectures in many deep learning fields like Natural Language Processing, Computer Vision or Speech processing. It may encourage the direct use of Transformers in the constrained tasks,…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-29 Youness Dkhissi , Valentin Vielzeuf , Elys Allesiardo , Anthony Larcher

Large Language Models (LLMs) are currently under exploration for various tasks, including Automatic Speech Recognition (ASR), Machine Translation (MT), and even End-to-End Speech Translation (ST). In this paper, we present KIT's offline…

Computation and Language · Computer Science 2024-06-25 Sai Koneru , Thai-Binh Nguyen , Ngoc-Quan Pham , Danni Liu , Zhaolin Li , Alexander Waibel , Jan Niehues

Automatic speech recognition (ASR) with an encoder equipped with self-attention, whether streaming or non-streaming, takes quadratic time in the length of the speech utterance. This slows down training and decoding, increase their cost, and…

Sound · Computer Science 2024-09-12 Titouan Parcollet , Rogier van Dalen , Shucong Zhang , Sourav Batthacharya

For spoken language translation (SLT) in live scenarios such as conferences, lectures and meetings, it is desirable to show the translation to the user as quickly as possible, avoiding an annoying lag between speaker and translated…

Computation and Language · Computer Science 2021-06-02 Yuekun Yao , Barry Haddow

Recent studies of streaming automatic speech recognition (ASR) recurrent neural network transducer (RNN-T)-based systems have fed the encoder with past contextual information in order to improve its word error rate (WER) performance. In…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-31 Alejandro Gomez-Alanis , Lukas Drude , Andreas Schwarz , Rupak Vignesh Swaminathan , Simon Wiesler

Automatic Speech Recognition (ASR) has reached impressive accuracy for high-resource languages, yet its utility in linguistic fieldwork remains limited. Recordings collected in fieldwork contexts present unique challenges, including…

Computation and Language · Computer Science 2025-06-25 Siyu Liang , Gina-Anne Levow

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible, while full-context ASR waits for the completion of a full speech utterance before emitting completed hypotheses. In this…

Computation and Language · Computer Science 2021-01-28 Jiahui Yu , Wei Han , Anmol Gulati , Chung-Cheng Chiu , Bo Li , Tara N. Sainath , Yonghui Wu , Ruoming Pang

Automatic speech recognition (ASR) has shown rapid advances in recent years but still degrades significantly in far-field and noisy environments. The recent development of self-supervised learning (SSL) technology can improve the ASR…

Sound · Computer Science 2022-05-05 Changfeng Gao , Gaofeng Cheng , Pengyuan Zhang

Sequence-to-sequence attention-based models integrate an acoustic, pronunciation and language model into a single neural network, which make them very suitable for multilingual automatic speech recognition (ASR). In this paper, we are…

Audio and Speech Processing · Electrical Eng. & Systems 2018-06-15 Shiyu Zhou , Shuang Xu , Bo Xu

Training deep neural networks for automatic speech recognition (ASR) requires large amounts of transcribed speech. This becomes a bottleneck for training robust models for accented speech which typically contains high variability in…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-11 Nilaksh Das , Sravan Bodapati , Monica Sunkara , Sundararajan Srinivasan , Duen Horng Chau

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

Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…

Computation and Language · Computer Science 2026-03-11 Yen-Ju Lu , Yashesh Gaur , Wei Zhou , Benjamin Muller , Jesus Villalba , Najim Dehak , Luke Zettlemoyer , Gargi Ghosh , Mike Lewis , Srinivasan Iyer , Duc Le