b'Shujie Liu'

research

∙ 08/24/2023

WavMark: Watermarking for Audio Generation

Recent breakthroughs in zero-shot voice synthesis have enabled imitating...

0 Guangyu Chen, et al. ∙

research

∙ 06/28/2023

Accelerating Transducers through Adjacent Token Merging

Recent end-to-end automatic speech recognition (ASR) systems often utili...

0 Yuang Li, et al. ∙

research

∙ 06/28/2023

Prompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognition

The integration of Language Models (LMs) has proven to be an effective w...

0 Yuang Li, et al. ∙

research

∙ 05/24/2023

ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation

Joint speech-language training is challenging due to the large demand fo...

0 Chenyang Le, et al. ∙

research

∙ 03/20/2023

Code-Switching Text Generation and Injection in Mandarin-English ASR

Code-switching speech refers to a means of expression by mixing two or m...

0 Haibin Yu, et al. ∙

research

∙ 03/01/2023

Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training

We propose gated language experts to improve multilingual transformer tr...

0 Eric Sun, et al. ∙

research

∙ 01/05/2023

Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

We introduce a language modeling approach for text to speech synthesis (...

4 Chengyi Wang, et al. ∙

research

∙ 12/18/2022

BEATs: Audio Pre-Training with Acoustic Tokenizers

The massive growth of self-supervised learning (SSL) has been witnessed ...

0 Sanyuan Chen, et al. ∙

research

∙ 11/21/2022

VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning

Although speech is a simple and effective way for humans to communicate ...

0 Qiushi Zhu, et al. ∙

research

∙ 11/18/2022

Exploring WavLM on Speech Enhancement

There is a surge in interest in self-supervised learning approaches for ...

0 Hyungchan Song, et al. ∙

research

∙ 11/17/2022

LongFNT: Long-form Speech Recognition with Factorized Neural Transducer

Traditional automatic speech recognition (ASR) systems usually focus on ...

0 Xun Gong, et al. ∙

research

∙ 11/05/2022

LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers

End-to-end formulation of automatic speech recognition (ASR) and speech ...

0 Peidong Wang, et al. ∙

research

∙ 11/02/2022

Two-Stream Network for Sign Language Recognition and Translation

Sign languages are visual languages using manual articulations and non-m...

0 Yutong Chen, et al. ∙

research

∙ 10/31/2022

Joint Pre-Training with Speech and Bilingual Text for Direct Speech to Speech Translation

Direct speech-to-speech translation (S2ST) is an attractive research top...

0 Kun Wei, et al. ∙

research

∙ 10/07/2022

SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training

The rapid development of single-modal pre-training has prompted research...

0 Ziqiang Zhang, et al. ∙

research

∙ 09/30/2022

SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data

How to boost speech pre-training with textual data is an unsolved proble...

0 Ziqiang Zhang, et al. ∙

research

∙ 06/12/2022

The YiTrans End-to-End Speech Translation System for IWSLT 2022 Offline Shared Task

This paper describes the submission of our end-to-end YiTrans speech tra...

0 Ziqiang Zhang, et al. ∙

research

∙ 04/27/2022

Ultra Fast Speech Separation Model with Teacher Student Learning

Transformer has been successfully applied to speech separation recently ...

0 Sanyuan Chen, et al. ∙

research

∙ 04/27/2022

Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?

Recently, self-supervised learning (SSL) has demonstrated strong perform...

0 Sanyuan Chen, et al. ∙

research

∙ 04/07/2022

Speech Pre-training with Acoustic Piece

Previous speech pre-training methods, such as wav2vec2.0 and HuBERT, pre...

0 Shuo Ren, et al. ∙

research

∙ 03/31/2022

Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data

This paper studies a novel pre-training technique with unpaired speech d...

0 Junyi Ao, et al. ∙

research

∙ 12/16/2021

Self-Supervised Learning for speech recognition with Intermediate layer supervision

Recently, pioneer work finds that speech pre-trained models can solve fu...

0 Chengyi Wang, et al. ∙

research

∙ 10/27/2021

Separating Long-Form Speech with Group-Wise Permutation Invariant Training

Multi-talker conversational speech processing has drawn many interests f...

0 Wangyou Zhang, et al. ∙

research

∙ 10/26/2021

WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing

Self-supervised learning (SSL) achieves great success in speech recognit...

0 Sanyuan Chen, et al. ∙

research

∙ 10/23/2021

Optimizing Alignment of Speech and Language Latent Spaces for End-to-End Speech Recognition and Understanding

The advances in attention-based encoder-decoder (AED) networks have brou...

1 Wei Wang, et al. ∙

research

∙ 10/12/2021

Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification

The speech representations learned from large-scale unlabeled data have ...

0 Zhengyang Chen, et al. ∙

research

∙ 10/12/2021

UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training

Self-supervised learning (SSL) is a long-standing goal for speech proces...

0 Sanyuan Chen, et al. ∙

research

∙ 09/12/2021

Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation

Although pre-training models have achieved great success in dialogue gen...

0 Leyang Cui, et al. ∙

research

∙ 07/13/2021

A Configurable Multilingual Model is All You Need to Recognize All Languages

Multilingual automatic speech recognition (ASR) models have shown great ...

0 Long Zhou, et al. ∙

research

∙ 07/05/2021

Investigation of Practical Aspects of Single Channel Speech Separation for ASR

Speech separation has been successfully applied as a frontend processing...

0 Jian Wu, et al. ∙

research

∙ 01/19/2021

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data

In this paper, we propose a unified pre-training approach called UniSpee...

21 Chengyi Wang, et al. ∙

research

∙ 10/23/2020

Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer

With its strong modeling capacity that comes from a multi-head and multi...

0 Sanyuan Chen, et al. ∙

research

∙ 10/22/2020

Microsoft Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2020

This paper describes the Microsoft speaker diarization system for monaur...

0 Xiong Xiao, et al. ∙

research

∙ 10/22/2020

Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset

Recently, Transformer based end-to-end models have achieved great succes...

0 Xie Chen, et al. ∙

research

∙ 09/22/2020

CodeBLEU: a Method for Automatic Evaluation of Code Synthesis

Evaluation metrics play a vital role in the growth of an area as it defi...

0 Shuo Ren, et al. ∙

research

∙ 09/17/2020

GraphCodeBERT: Pre-training Code Representations with Data Flow

Pre-trained models for programming language have achieved dramatic empir...

0 Daya Guo, et al. ∙

research

∙ 08/13/2020

Continuous Speech Separation with Conformer

Continuous speech separation plays a vital role in complicated speech re...

0 Sanyuan Chen, et al. ∙

research

∙ 05/28/2020

On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition

Recently, there has been a strong push to transition from hybrid models ...

0 Jinyu Li, et al. ∙

research

∙ 05/18/2020

MoBoAligner: a Neural Alignment Model for Non-autoregressive TTS with Monotonic Boundary Search

To speed up the inference of neural speech synthesis, non-autoregressive...

0 Naihan Li, et al. ∙

research

∙ 04/21/2020

Curriculum Pre-training for End-to-End Speech Translation

End-to-end speech translation poses a heavy burden on the encoder, becau...

0 Chengyi Wang, et al. ∙

research

∙ 04/09/2020

MuTual: A Dataset for Multi-Turn Dialogue Reasoning

Non-task oriented dialogue systems have achieved great success in recent...

0 Leyang Cui, et al. ∙

research

∙ 12/06/2019

Semantic Mask for Transformer based End-to-End Speech Recognition

Attention-based encoder-decoder model has achieved impressive results fo...

0 Chengyi Wang, et al. ∙

research

∙ 10/18/2019

Unsupervised Context Rewriting for Open Domain Conversation

Context modeling has a pivotal role in open domain conversation. Existin...

0 Kun Zhou, et al. ∙

research

∙ 09/17/2019

Bridging the Gap between Pre-Training and Fine-Tuning for End-to-End Speech Translation

End-to-end speech translation, a hot topic in recent years, aims to tran...

0 Chengyi Wang, et al. ∙

research

∙ 09/05/2019

Accelerating Transformer Decoding via a Hybrid of Self-attention and Recurrent Neural Network

Due to the highly parallelizable architecture, Transformer is faster to ...

0 Chengyi Wang, et al. ∙

research

∙ 09/05/2019

Source Dependency-Aware Transformer with Supervised Self-Attention

Recently, Transformer has achieved the state-of-the-art performance on m...

0 Chengyi Wang, et al. ∙

research

∙ 08/31/2019

Explicit Cross-lingual Pre-training for Unsupervised Machine Translation

Pre-training has proven to be effective in unsupervised machine translat...

0 Shuo Ren, et al. ∙

research

∙ 01/14/2019

Unsupervised Neural Machine Translation with SMT as Posterior Regularization

Without real bilingual corpus available, unsupervised Neural Machine Tra...

0 Shuo Ren, et al. ∙

research

∙ 09/19/2018

Close to Human Quality TTS with Transformer

Although end-to-end neural text-to-speech (TTS) methods (such as Tacotro...

0 Naihan Li, et al. ∙

research

∙ 08/24/2018

Approximate Distribution Matching for Sequence-to-Sequence Learning

Sequence-to-Sequence models were introduced to tackle many real-life pro...

2 Wenhu Chen, et al. ∙

Shujie Liu

Featured Co-authors