English
Related papers

Related papers: End-to-End Multi-speaker Speech Recognition with T…

200 papers

This paper proposes an efficient memory transformer Emformer for low latency streaming speech recognition. In Emformer, the long-range history context is distilled into an augmented memory bank to reduce self-attention's computation…

This paper presents an audio visual automatic speech recognition (AV-ASR) system using a Transformer-based architecture. We particularly focus on the scene context provided by the visual information, to ground the ASR. We extract…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-01 Georgios Paraskevopoulos , Srinivas Parthasarathy , Aparna Khare , Shiva Sundaram

With its strong modeling capacity that comes from a multi-head and multi-layer structure, Transformer is a very powerful model for learning a sequential representation and has been successfully applied to speech separation recently.…

Sound · Computer Science 2020-10-26 Sanyuan Chen , Yu Wu , Zhuo Chen , Takuya Yoshioka , Shujie Liu , Jinyu Li

We present a comprehensive study on building and adapting RNN transducer (RNN-T) models for spoken language understanding(SLU). These end-to-end (E2E) models are constructed in three practical settings: a case where verbatim transcripts are…

Computation and Language · Computer Science 2021-04-09 Samuel Thomas , Hong-Kwang J. Kuo , George Saon , Zoltán Tüske , Brian Kingsbury , Gakuto Kurata , Zvi Kons , Ron Hoory

In this work, we introduce a simple yet efficient post-processing model for automatic speech recognition (ASR). Our model has Transformer-based encoder-decoder architecture which "translates" ASR model output into grammatically and…

Computation and Language · Computer Science 2019-10-24 Oleksii Hrinchuk , Mariya Popova , Boris Ginsburg

Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition. In this work, we show that such models can achieve competitive results on the Switchboard 300h and LibriSpeech 1000h…

Computation and Language · Computer Science 2019-08-06 Albert Zeyer , Kazuki Irie , Ralf Schlüter , Hermann Ney

Recently, deep learning-based beamforming algorithms have shown promising performance in target speech extraction tasks. However, most systems do not fully utilize spatial information. In this paper, we propose a target speech extraction…

Sound · Computer Science 2023-06-29 Aoqi Guo , Junnan Wu , Peng Gao , Wenbo Zhu , Qinwen Guo , Dazhi Gao , Yujun Wang

Sequence classification is essential in NLP for understanding and categorizing language patterns in tasks like sentiment analysis, intent detection, and topic classification. Transformer-based models, despite achieving state-of-the-art…

Computation and Language · Computer Science 2025-09-30 Hongbo Liu , Jia Xu

Many of the current state-of-the-art Large Vocabulary Continuous Speech Recognition Systems (LVCSR) are hybrids of neural networks and Hidden Markov Models (HMMs). Most of these systems contain separate components that deal with the…

Computation and Language · Computer Science 2016-03-16 Dzmitry Bahdanau , Jan Chorowski , Dmitriy Serdyuk , Philemon Brakel , Yoshua Bengio

End-to-end training of deep learning-based models allows for implicit learning of intermediate representations based on the final task loss. However, the end-to-end approach ignores the useful domain knowledge encoded in explicit…

Computation and Language · Computer Science 2017-04-20 Shubham Toshniwal , Hao Tang , Liang Lu , Karen Livescu

Speech recognition on smart devices is challenging owing to the small memory footprint. Hence small size ASR models are desirable. With the use of popular transducer-based models, it has become possible to practically deploy streaming…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-11 Nauman Dawalatabad , Tushar Vatsal , Ashutosh Gupta , Sungsoo Kim , Shatrughan Singh , Dhananjaya Gowda , Chanwoo Kim

Speech enhancement is a demanding task in automated speech processing pipelines, focusing on separating clean speech from noisy channels. Transformer based models have recently bested RNN and CNN models in speech enhancement, however at the…

Sound · Computer Science 2023-08-07 Jinyu Long , Jetic Gū , Binhao Bai , Zhibo Yang , Ping Wei , Junli Li

In this paper, we describe the use of recurrent neural networks to capture sequential information from the self-attention representations to improve the Transformers. Although self-attention mechanism provides a means to exploit long…

Computation and Language · Computer Science 2021-04-06 Tze Yuang Chong , Xuyang Wang , Lin Yang , Junjie Wang

This paper describes a speaker diarization model based on target speaker voice activity detection (TS-VAD) using transformers. To overcome the original TS-VAD model's drawback of being unable to handle an arbitrary number of speakers, we…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-27 Dongmei Wang , Xiong Xiao , Naoyuki Kanda , Takuya Yoshioka , Jian Wu

In this paper, we propose to use pre-trained features from end-to-end ASR models to solve speech sentiment analysis as a down-stream task. We show that end-to-end ASR features, which integrate both acoustic and text information from speech,…

Computation and Language · Computer Science 2020-03-06 Zhiyun Lu , Liangliang Cao , Yu Zhang , Chung-Cheng Chiu , James Fan

With the development of teleconferencing and in-vehicle voice assistants, far-field multi-speaker speech recognition has become a hot research topic. Recently, a multi-channel transformer (MCT) has been proposed, which demonstrates the…

Sound · Computer Science 2026-01-07 Guo Yifan , Tian Yao , Suo Hongbin , Wan Yulong

Recurrent transducer models have emerged as a promising solution for speech recognition on the current and next generation smart devices. The transducer models provide competitive accuracy within a reasonable memory footprint alleviating…

End-to-end models have gradually become the main technical stream for voice trigger, aiming to achieve an utmost prediction accuracy but with a small footprint. In present paper, we propose an end-to-end voice trigger framework, namely…

Sound · Computer Science 2022-10-07 Zixing Zhang , Thorin Farnsworth , Senling Lin , Salah Karout

Recurrent neural network transducer (RNN-T) is an end-to-end speech recognition framework converting input acoustic frames into a character sequence. The state-of-the-art encoder network for RNN-T is the Conformer, which can effectively…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-20 Juntae Kim , Jeehye Lee

Recent advances in self-supervised learning (SSL) on Transformers have significantly improved speaker verification (SV) by providing domain-general speech representations. However, existing approaches have underutilized the multi-layered…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-16 Jin Sob Kim , Hyun Joon Park , Wooseok Shin , Juan Yun , Sung Won Han