English
Related papers

Related papers: Low Latency ASR for Simultaneous Speech Translatio…

200 papers

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

Transformer-based models have achieved state-of-the-art performance on speech translation tasks. However, the model architecture is not efficient enough for streaming scenarios since self-attention is computed over an entire input sequence…

Computation and Language · Computer Science 2020-11-03 Xutai Ma , Yongqiang Wang , Mohammad Javad Dousti , Philipp Koehn , Juan Pino

Harnessing pre-trained LLMs to improve ASR systems, particularly for low-resource languages, is now an emerging area of research. Existing methods range from using LLMs for ASR error correction to tightly coupled systems that replace the…

Computation and Language · Computer Science 2024-08-30 Ashish Mittal , Darshan Prabhu , Sunita Sarawagi , Preethi Jyothi

In this work we propose an inference technique, asynchronous revision, to unify streaming and non-streaming speech recognition models. Specifically, we achieve dynamic latency with only one model by using arbitrary right context during…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-04 Mingkun Huang , Meng Cai , Jun Zhang , Yang Zhang , Yongbin You , Yi He , Zejun Ma

In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel…

Computation and Language · Computer Science 2019-10-29 Qiao Cheng , Meiyuan Fang , Yaqian Han , Jin Huang , Yitao Duan

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

Artificial Intelligence · Computer Science 2021-03-19 Md Akmal Haidar , Chao Xing , Mehdi Rezagholizadeh

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

In recent years, developing a speech understanding system that classifies a waveform to structured data, such as intents and slots, without first transcribing the speech to text has emerged as an interesting research problem. This work…

Computer Vision and Pattern Recognition · Computer Science 2020-11-11 Mohamed Mhiri , Samuel Myer , Vikrant Singh Tomar

Transfer learning (TL) is widely used in conventional hybrid automatic speech recognition (ASR) system, to transfer the knowledge from source to target language. TL can be applied to end-to-end (E2E) ASR system such as recurrent neural…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-18 Vikas Joshi , Rui Zhao , Rupesh R. Mehta , Kshitiz Kumar , Jinyu Li

Boosted by the simultaneous translation shared task at IWSLT 2020, promising end-to-end online speech translation approaches were recently proposed. They consist in incrementally encoding a speech input (in a source language) and decoding…

Computation and Language · Computer Science 2021-06-15 Ha Nguyen , Yannick Estève , Laurent Besacier

Conventional spoken language translation (SLT) systems are pipeline based systems, where we have an Automatic Speech Recognition (ASR) system to convert the modality of source from speech to text and a Machine Translation (MT) systems to…

Streaming ASR with strict latency constraints is required in many speech recognition applications. In order to achieve the required latency, streaming ASR models sacrifice accuracy compared to non-streaming ASR models due to lack of future…

Computation and Language · Computer Science 2022-03-30 Jay Mahadeokar , Yangyang Shi , Ke Li , Duc Le , Jiedan Zhu , Vikas Chandra , Ozlem Kalinli , Michael L Seltzer

Encoder-decoder models provide a generic architecture for sequence-to-sequence tasks such as speech recognition and translation. While offline systems are often evaluated on quality metrics like word error rates (WER) and BLEU, latency is…

Computation and Language · Computer Science 2020-10-14 Danni Liu , Gerasimos Spanakis , Jan Niehues

This paper presents a newly developed, simultaneous neural speech-to-speech translation system and its evaluation. The system consists of three fully-incremental neural processing modules for automatic speech recognition (ASR), machine…

Computation and Language · Computer Science 2020-11-12 Katsuhito Sudoh , Takatomo Kano , Sashi Novitasari , Tomoya Yanagita , Sakriani Sakti , Satoshi Nakamura

Large language model (LLM)-based automatic speech recognition (ASR) has recently attracted a lot of attention due to its high recognition accuracy and enhanced multi-dialect support. However, the high decoding latency of LLMs challenges the…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-29 Linye Wei , Shuzhang Zhong , Songqiang Xu , Runsheng Wang , Ru Huang , Meng Li

For many streaming automatic speech recognition tasks, it is important to provide timely intermediate streaming results, while refining a high quality final result. This can be done using a multi-stage architecture, where a small…

Computation and Language · Computer Science 2023-12-18 Antoine Bruguier , David Qiu , Yanzhang He

Normally, a system that translates speech into text consists of separate modules for speech recognition and text-to-text translation. Combining those tasks into a SpeechLLM promises to exploit paralinguistic information in the speech and to…

Computation and Language · Computer Science 2026-05-15 Titouan Parcollet , Shucong Zhang , Xianrui Zheng , Rogier C. van Dalen

Sequence transducers, such as the RNN-T and the Conformer-T, are one of the most promising models of end-to-end speech recognition, especially in streaming scenarios where both latency and accuracy are important. Although various methods,…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-07 Yusuke Shinohara , Shinji Watanabe

Cascaded speech-to-speech translation systems often suffer from the error accumulation problem and high latency, which is a result of cascaded modules whose inference delays accumulate. In this paper, we propose a transducer-based speech…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-07 Jinzheng Zhao , Niko Moritz , Egor Lakomkin , Ruiming Xie , Zhiping Xiu , Katerina Zmolikova , Zeeshan Ahmed , Yashesh Gaur , Duc Le , Christian Fuegen

Recent advances in sequence modeling have highlighted the strengths of the transformer architecture, especially in achieving state-of-the-art machine translation results. However, depending on the up-stream systems, e.g., speech…

Computation and Language · Computer Science 2019-06-14 Pei Zhang , Boxing Chen , Niyu Ge , Kai Fan