English
Related papers

Related papers: Minimum Latency Training Strategies for Streaming …

200 papers

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

The transformer is a fundamental building block in deep learning, and the attention mechanism is the transformer's core component. Self-supervised speech representation learning (SSRL) represents a popular use-case for the transformer…

Sound · Computer Science 2024-03-19 Jianbo Ma , Siqi Pan , Deepak Chandran , Andrea Fanelli , Richard Cartwright

Speaker anonymization aims to conceal cues to speaker identity while preserving linguistic content. Current machine learning based approaches require substantial computational resources, hindering real-time streaming applications. To…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-04 Waris Quamer , Ricardo Gutierrez-Osuna

End-to-end Spoken Language Understanding (SLU) models are made increasingly large and complex to achieve the state-ofthe-art accuracy. However, the increased complexity of a model can also introduce high risk of over-fitting, which is a…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-14 Xueli Jia , Jianzong Wang , Zhiyong Zhang , Ning Cheng , Jing Xiao

Deploying high-quality automatic speech recognition (ASR) on edge devices requires models that jointly optimize accuracy, latency, and memory footprint while operating entirely on CPU without GPU acceleration. We conduct a systematic…

Artificial Intelligence · Computer Science 2026-04-21 Nenad Banfic , David Fan , Kunal Vaishnavi , Sam Kemp , Sunghoon Choi , Rui Ren , Sayan Shaw , Meng Tang

Recently, the recurrent neural network transducer (RNN-T) architecture has become an emerging trend in end-to-end automatic speech recognition research due to its advantages of being capable for online streaming speech recognition. However,…

Computation and Language · Computer Science 2020-05-05 Hu Hu , Rui Zhao , Jinyu Li , Liang Lu , Yifan Gong

The black-box nature of end-to-end speech translation (E2E ST) systems makes it difficult to understand how source language inputs are being mapped to the target language. To solve this problem, we would like to simultaneously generate…

Computation and Language · Computer Science 2022-11-14 Motoi Omachi , Brian Yan , Siddharth Dalmia , Yuya Fujita , Shinji Watanabe

Large Language Model (LLM) based text-to-speech (TTS) systems have demonstrated remarkable capabilities in handling large speech datasets and generating natural speech for new speakers. However, LLM-based TTS models are not robust as the…

We investigate a monotonic multihead attention (MMA) by extending hard monotonic attention to Transformer-based automatic speech recognition (ASR) for online streaming applications. For streaming inference, all monotonic attention (MA)…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-01 Hirofumi Inaguma , Masato Mimura , Tatsuya Kawahara

Online Transformer-based automatic speech recognition (ASR) systems have been extensively studied due to the increasing demand for streaming applications. Recently proposed Decoder-end Adaptive Computation Steps (DACS) algorithm for online…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-27 Mohan Li , Catalin Zorila , Rama Doddipatla

Joint optimization of multi-channel front-end and automatic speech recognition (ASR) has attracted much interest. While promising results have been reported for various tasks, past studies on its meeting transcription application were…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-30 Xiaofei Wang , Naoyuki Kanda , Yashesh Gaur , Zhuo Chen , Zhong Meng , Takuya Yoshioka

End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a single neural network. However, as a drawback, training of…

Computation and Language · Computer Science 2022-02-17 Yotaro Kubo , Shigeki Karita , Michiel Bacchiani

Automatic transcription of stuttered speech remains a challenge, even for modern end-to-end (E2E) automatic speech recognition (ASR) frameworks. Dysfluencies and fluency-shaping artifacts are often overlooked, resulting in non-verbatim…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-03 Kashaf Gulzar , Dominik Wagner , Sebastian P. Bayerl , Florian Hönig , Tobias Bocklet , Korbinian Riedhammer

Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in…

Computation and Language · Computer Science 2017-12-06 Tara N. Sainath , Chung-Cheng Chiu , Rohit Prabhavalkar , Anjuli Kannan , Yonghui Wu , Patrick Nguyen , Zhifeng Chen

Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or…

Computation and Language · Computer Science 2019-02-21 Ozan Caglayan , Ramon Sanabria , Shruti Palaskar , Loïc Barrault , Florian Metze

In this work, we develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR). For untranscribed speech data, the hypothesis from an ASR system must be used as a…

Computation and Language · Computer Science 2021-12-23 Kenichi Kumatani , Dimitrios Dimitriadis , Yashesh Gaur , Robert Gmyr , Sefik Emre Eskimez , Jinyu Li , Michael Zeng

This paper proposes a novel label-synchronous speech-to-text alignment technique for automatic speech recognition (ASR). The speech-to-text alignment is a problem of splitting long audio recordings with un-aligned transcripts into…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-22 Yusuke Kida , Tatsuya Komatsu , Masahito Togami

Although end-to-end neural text-to-speech (TTS) methods (such as Tacotron2) are proposed and achieve state-of-the-art performance, they still suffer from two problems: 1) low efficiency during training and inference; 2) hard to model long…

Computation and Language · Computer Science 2019-01-31 Naihan Li , Shujie Liu , Yanqing Liu , Sheng Zhao , Ming Liu , Ming Zhou

Recently, online end-to-end ASR has gained increasing attention. However, the performance of online systems still lags far behind that of offline systems, with a large gap in quality of recognition. For specific scenarios, we can trade-off…

Sound · Computer Science 2020-10-28 Zhifu Gao , Shiliang Zhang , Ming Lei , Ian McLoughlin

This work proposes a frame-wise online/streaming end-to-end neural diarization (EEND) method, which detects speaker activities in a frame-in-frame-out fashion. The proposed model mainly consists of a causal embedding encoder and an online…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-09 Di Liang , Xiaofei Li