papers

Publications (32)

cs.AI2020

AutoSpeech 2020: The Second Automated Machine Learning Challenge for Speech Classification

Jingsong Wang, Tom Ko, Zhen Xu +4

The AutoSpeech challenge calls for automated machine learning (AutoML) solutions to automate the process of applying machine learning to speech processing tasks. These tasks, which…

eess.AS2021

CL4AC: A Contrastive Loss for Audio Captioning

Xubo Liu, Qiushi Huang, Xinhao Mei +4

Automated Audio captioning (AAC) is a cross-modal translation task that aims to use natural language to describe the content of an audio clip. As shown in the submissions received…

eess.AS2026

Controllable Accent Normalization via Discrete Diffusion

Qibing Bai, Yuhan Du, Tom Ko +3

Existing accent normalization methods do not typically offer control over accent strength, yet many applications-such as language learning and dubbing-require tunable accent retent…

cs.SD2022

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

Junyi Ao, Ziqiang Zhang, Long Zhou +7

This paper studies a novel pre-training technique with unpaired speech data, Speech2C, for encoder-decoder based automatic speech recognition (ASR). Within a multi-task learning fr…

eess.AS2022

Multi-View Self-Attention Based Transformer for Speaker Recognition

Rui Wang, Junyi Ao, Long Zhou +5

Initially developed for natural language processing (NLP), Transformer model is now widely used for speech processing tasks such as speaker recognition, due to its powerful sequenc…

cs.SD2023

MOSPC: MOS Prediction Based on Pairwise Comparison

Kexin Wang, Yunlong Zhao, Qianqian Dong +2

As a subjective metric to evaluate the quality of synthesized speech, Mean opinion score~(MOS) usually requires multiple annotators to score the same speech. Such an annotation app…

eess.AS2021

An Encoder-Decoder Based Audio Captioning System With Transfer and Reinforcement Learning

Xinhao Mei, Qiushi Huang, Xubo Liu +10

Automated audio captioning aims to use natural language to describe the content of audio data. This paper presents an audio captioning system with an encoder-decoder architecture,…

cs.CL2024

Selective Prompting Tuning for Personalized Conversations with LLMs

Qiushi Huang, Xubo Liu, Tom Ko +4

In conversational AI, personalizing dialogues with persona profiles and contextual understanding is essential. Despite large language models' (LLMs) improved response coherence, ef…

cs.CV2023

Leveraging per Image-Token Consistency for Vision-Language Pre-training

Yunhao Gou, Tom Ko, Hansi Yang +3

Most existing vision-language pre-training (VLP) approaches adopt cross-modal masked language modeling (CMLM) to learn vision-language associations. However, we find that CMLM is i…

cs.CV2020

MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization

Yangbin Chen, Yun Ma, Tom Ko +2

Model-Agnostic Meta-Learning (MAML) and its variants are popular few-shot classification methods. They train an initializer across a variety of sampled learning tasks (also known a…

cs.CL2023

DUB: Discrete Unit Back-translation for Speech Translation

Dong Zhang, Rong Ye, Tom Ko +2

How can speech-to-text translation (ST) perform as well as machine translation (MT)? The key point is to bridge the modality gap between speech and text so that useful MT technique…

cs.CL2023

Speech Translation with Large Language Models: An Industrial Practice

Zhichao Huang, Rong Ye, Tom Ko +4

Given the great success of large language models (LLMs) across various tasks, in this paper, we introduce LLM-ST, a novel and effective speech translation model constructed upon a…

cs.CL2023

GigaST: A 10,000-hour Pseudo Speech Translation Corpus

Rong Ye, Chengqi Zhao, Tom Ko +4

This paper introduces GigaST, a large-scale pseudo speech translation (ST) corpus. We create the corpus by translating the text in GigaSpeech, an English ASR corpus, into German an…

cs.CL2023

Token-Level Supervised Contrastive Learning for Punctuation Restoration

Qiushi Huang, Tom Ko, H Lilian Tang +2

Punctuation is critical in understanding natural language text. Currently, most automatic speech recognition (ASR) systems do not generate punctuation, which affects the performanc…

eess.AS2022

SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing

Junyi Ao, Rui Wang, Long Zhou +11

Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores th…

cs.CL2020

An Investigation of Few-Shot Learning in Spoken Term Classification

Yangbin Chen, Tom Ko, Lifeng Shang +3

In this paper, we investigate the feasibility of applying few-shot learning algorithms to a speech task. We formulate a user-defined scenario of spoken term classification as a few…

cs.CL2024

Learning Retrieval Augmentation for Personalized Dialogue Generation

Qiushi Huang, Shuai Fu, Xubo Liu +4

Personalized dialogue generation, focusing on generating highly tailored responses by leveraging persona profiles and dialogue context, has gained significant attention in conversa…

eess.AS2022

LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

Rui Wang, Qibing Bai, Junyi Ao +6

Self-supervised speech representation learning has shown promising results in various speech processing tasks. However, the pre-trained models, e.g., HuBERT, are storage-intensive…

cs.SD2023

CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning

Chutong Meng, Junyi Ao, Tom Ko +2

Speech is the surface form of a finite set of phonetic units, which can be represented by discrete codes. We propose the Code BERT (CoBERT) approach for self-supervised speech repr…

cs.CL2024

Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent

Shanbo Cheng, Zhichao Huang, Tom Ko +4

In this paper, we present Cross Language Agent -- Simultaneous Interpretation, CLASI, a high-quality and human-like Simultaneous Speech Translation (SiST) System. Inspired by profe…

cs.CL2022

M3ST: Mix at Three Levels for Speech Translation

Xuxin Cheng, Qianqian Dong, Fengpeng Yue +3

How to solve the data scarcity problem for end-to-end speech-to-text translation (ST)? It's well known that data augmentation is an efficient method to improve performance for many…

cs.CL2023

CTC-based Non-autoregressive Speech Translation

Chen Xu, Xiaoqian Liu, Xiaowen Liu +9

Combining end-to-end speech translation (ST) and non-autoregressive (NAR) generation is promising in language and speech processing for their advantages of less error propagation a…

cs.CL2023

Recent Advances in Direct Speech-to-text Translation

Chen Xu, Rong Ye, Qianqian Dong +5

Recently, speech-to-text translation has attracted more and more attention and many studies have emerged rapidly. In this paper, we present a comprehensive survey on direct speech…

cs.CL2021

Exploring Machine Speech Chain for Domain Adaptation and Few-Shot Speaker Adaptation

Fengpeng Yue, Yan Deng, Lei He +1

Machine Speech Chain, which integrates both end-to-end (E2E) automatic speech recognition (ASR) and text-to-speech (TTS) into one circle for joint training, has been proven to be e…

cs.SD2021

Auto-KWS 2021 Challenge: Task, Datasets, and Baselines

Jingsong Wang, Yuxuan He, Chunyu Zhao +5

Auto-KWS 2021 challenge calls for automated machine learning (AutoML) solutions to automate the process of applying machine learning to a customized keyword spotting task. Compared…

eess.AS2024

WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research

Xinhao Mei, Chutong Meng, Haohe Liu +6

The advancement of audio-language (AL) multimodal learning tasks has been significant in recent years. However, researchers face challenges due to the costly and time-consuming col…

cs.CL2023

PolyVoice: Language Models for Speech to Speech Translation

Qianqian Dong, Zhiying Huang, Qiao Tian +15

We propose PolyVoice, a language model-based framework for speech-to-speech translation (S2ST) system. Our framework consists of two language models: a translation language model a…

eess.AS2024

RepCodec: A Speech Representation Codec for Speech Tokenization

Zhichao Huang, Chutong Meng, Tom Ko

With recent rapid growth of large language models (LLMs), discrete speech tokenization has played an important role for injecting speech into LLMs. However, this discretization giv…

cs.CL2022

Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation

Qianqian Dong, Fengpeng Yue, Tom Ko +3

Direct Speech-to-speech translation (S2ST) has drawn more and more attention recently. The task is very challenging due to data scarcity and complex speech-to-speech mapping. In th…

eess.AS2022

A Study of Modeling Rising Intonation in Cantonese Neural Speech Synthesis

Qibing Bai, Tom Ko, Yu Zhang

In human speech, the attitude of a speaker cannot be fully expressed only by the textual content. It has to come along with the intonation. Declarative questions are commonly used…

eess.AS2023

Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention

Xubo Liu, Qiushi Huang, Xinhao Mei +10

Audio captioning aims to generate text descriptions of audio clips. In the real world, many objects produce similar sounds. How to accurately recognize ambiguous sounds is a major…

cs.CL2024

Personalized Dialogue Generation with Persona-Adaptive Attention

Qiushi Huang, Yu Zhang, Tom Ko +4

Persona-based dialogue systems aim to generate consistent responses based on historical context and predefined persona. Unlike conventional dialogue generation, the persona-based d…