Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Tom Ko

Tom Ko

M3ST: Mix at Three Levels for Speech Translation

Dec 07, 2022
Xuxin Cheng, Qianqian Dong, Fengpeng Yue, Tom Ko, Mingxuan Wang, Yuexian Zou

Figure 1 for M3ST: Mix at Three Levels for Speech Translation

Figure 2 for M3ST: Mix at Three Levels for Speech Translation

Figure 3 for M3ST: Mix at Three Levels for Speech Translation

Figure 4 for M3ST: Mix at Three Levels for Speech Translation

* Submitted to ICASSP 2023

Access Paper or Ask Questions

Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention

Oct 28, 2022
Xubo Liu, Qiushi Huang, Xinhao Mei, Haohe Liu, Qiuqiang Kong, Jianyuan Sun, Shengchen Li, Tom Ko, Yu Zhang, Lilian H. Tang, Mark D. Plumbley, Volkan Kılıç, Wenwu Wang

Figure 1 for Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention

Figure 2 for Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention

* Submitted to ICASSP 2023

Access Paper or Ask Questions

Personalized Dialogue Generation with Persona-Adaptive Attention

Oct 27, 2022
Qiushi Huang, Yu Zhang, Tom Ko, Xubo Liu, Bo Wu, Wenwu Wang, Lilian Tang

Figure 1 for Personalized Dialogue Generation with Persona-Adaptive Attention

Figure 2 for Personalized Dialogue Generation with Persona-Adaptive Attention

Figure 3 for Personalized Dialogue Generation with Persona-Adaptive Attention

Figure 4 for Personalized Dialogue Generation with Persona-Adaptive Attention

* 8 pages, 3 figures

Access Paper or Ask Questions

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

Oct 08, 2022
Chutong Meng, Junyi Ao, Tom Ko, Mingxuan Wang, Haizhou Li

Figure 1 for CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning

Figure 2 for CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning

Figure 3 for CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning

Figure 4 for CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning

* Submitted to ICASSP 2023

Access Paper or Ask Questions

A Study of Modeling Rising Intonation in Cantonese Neural Speech Synthesis

Aug 03, 2022
Qibing Bai, Tom Ko, Yu Zhang

Figure 1 for A Study of Modeling Rising Intonation in Cantonese Neural Speech Synthesis

Figure 2 for A Study of Modeling Rising Intonation in Cantonese Neural Speech Synthesis

Figure 3 for A Study of Modeling Rising Intonation in Cantonese Neural Speech Synthesis

Figure 4 for A Study of Modeling Rising Intonation in Cantonese Neural Speech Synthesis

* Accepted by INTERSPEECH 2022

Access Paper or Ask Questions

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

May 18, 2022
Qianqian Dong, Fengpeng Yue, Tom Ko, Mingxuan Wang, Qibing Bai, Yu Zhang

Figure 1 for Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation

Figure 2 for Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation

Figure 3 for Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation

Figure 4 for Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation

* Submitted to INTERSPEECH 2022

Access Paper or Ask Questions

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

Apr 08, 2022
Rong Ye, Chengqi Zhao, Tom Ko, Chutong Meng, Tao Wang, Mingxuan Wang, Jun Cao

Figure 1 for GigaST: A 10,000-hour Pseudo Speech Translation Corpus

Figure 2 for GigaST: A 10,000-hour Pseudo Speech Translation Corpus

Figure 3 for GigaST: A 10,000-hour Pseudo Speech Translation Corpus

Figure 4 for GigaST: A 10,000-hour Pseudo Speech Translation Corpus

* Submitted to Interspeech 2022. GigaST dataset is available at https://st-benchmark.github.io/resources/GigaST

Access Paper or Ask Questions

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

Mar 31, 2022
Junyi Ao, Ziqiang Zhang, Long Zhou, Shujie Liu, Haizhou Li, Tom Ko, Lirong Dai, Jinyu Li, Yao Qian, Furu Wei

Figure 1 for Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data

Figure 2 for Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data

Figure 3 for Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data

Figure 4 for Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data

* Submitted to INTERSPEECH 2022

Access Paper or Ask Questions

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

Mar 29, 2022
Rui Wang, Qibing Bai, Junyi Ao, Long Zhou, Zhixiang Xiong, Zhihua Wei, Yu Zhang, Tom Ko, Haizhou Li

Figure 1 for LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

Figure 2 for LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

Figure 3 for LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

Figure 4 for LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

* 5 pages, 2 figures, submitted to Insterspeech 2022

Access Paper or Ask Questions