Picture for Jinyu Li

Jinyu Li

VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation

May 25, 2023
Tianrui Wang, Long Zhou, Ziqiang Zhang, Yu Wu, Shujie Liu, Yashesh Gaur, Zhuo Chen, Jinyu Li, Furu Wei

Figure 1 for VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation

Figure 2 for VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation

Figure 3 for VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation

Figure 4 for VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation

* Working in progress

Access Paper or Ask Questions

Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling

Mar 07, 2023
Ziqiang Zhang, Long Zhou, Chengyi Wang, Sanyuan Chen, Yu Wu, Shujie Liu, Zhuo Chen, Yanqing Liu, Huaming Wang, Jinyu Li, Lei He, Sheng Zhao, Furu Wei

Figure 1 for Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling

Figure 2 for Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling

Figure 3 for Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling

Figure 4 for Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling

* We encourage readers to listen to the audio samples on our demo page: \url{https://aka.ms/vallex}

Access Paper or Ask Questions

Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentation

Feb 22, 2023
Xiaoqiang Wang, Yanqing Liu, Jinyu Li, Sheng Zhao

Figure 1 for Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentation

Figure 2 for Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentation

Figure 3 for Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentation

* Accepted by ICASSP 2023

Access Paper or Ask Questions

Speaker Change Detection for Transformer Transducer ASR

Feb 16, 2023
Jian Wu, Zhuo Chen, Min Hu, Xiong Xiao, Jinyu Li

Figure 1 for Speaker Change Detection for Transformer Transducer ASR

Figure 2 for Speaker Change Detection for Transformer Transducer ASR

Figure 3 for Speaker Change Detection for Transformer Transducer ASR

Figure 4 for Speaker Change Detection for Transformer Transducer ASR

* 5 pages, 1 figure, accepted by ICASSP 2023

Access Paper or Ask Questions

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

Jan 05, 2023
Chengyi Wang, Sanyuan Chen, Yu Wu, Ziqiang Zhang, Long Zhou, Shujie Liu, Zhuo Chen, Yanqing Liu, Huaming Wang, Jinyu Li, Lei He, Sheng Zhao, Furu Wei

Figure 1 for Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Figure 2 for Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Figure 3 for Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Figure 4 for Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

* Working in progress

Access Paper or Ask Questions

Simulating realistic speech overlaps improves multi-talker ASR

Nov 17, 2022
Muqiao Yang, Naoyuki Kanda, Xiaofei Wang, Jian Wu, Sunit Sivasankaran, Zhuo Chen, Jinyu Li, Takuya Yoshioka

Figure 1 for Simulating realistic speech overlaps improves multi-talker ASR

Figure 2 for Simulating realistic speech overlaps improves multi-talker ASR

Figure 3 for Simulating realistic speech overlaps improves multi-talker ASR

Figure 4 for Simulating realistic speech overlaps improves multi-talker ASR

* v2: fix minor typo

Access Paper or Ask Questions