Alert button
Picture for Ke Hu

Ke Hu

Alert button

Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study

Jan 23, 2024
W. Ronny Huang, Cyril Allauzen, Tongzhou Chen, Kilol Gupta, Ke Hu, James Qin, Yu Zhang, Yongqiang Wang, Shuo-Yiin Chang, Tara N. Sainath

Viaarxiv icon

Feature Norm Regularized Federated Learning: Transforming Skewed Distributions into Global Insights

Dec 12, 2023
Ke Hu, WeiDong Qiu, Peng Tang

Viaarxiv icon

Improving Joint Speech-Text Representations Without Alignment

Aug 11, 2023
Cal Peyser, Zhong Meng, Ke Hu, Rohit Prabhavalkar, Andrew Rosenberg, Tara N. Sainath, Michael Picheny, Kyunghyun Cho

Figure 1 for Improving Joint Speech-Text Representations Without Alignment
Figure 2 for Improving Joint Speech-Text Representations Without Alignment
Figure 3 for Improving Joint Speech-Text Representations Without Alignment
Figure 4 for Improving Joint Speech-Text Representations Without Alignment
Viaarxiv icon

Mixture-of-Expert Conformer for Streaming Multilingual ASR

May 25, 2023
Ke Hu, Bo Li, Tara N. Sainath, Yu Zhang, Francoise Beaufays

Figure 1 for Mixture-of-Expert Conformer for Streaming Multilingual ASR
Figure 2 for Mixture-of-Expert Conformer for Streaming Multilingual ASR
Figure 3 for Mixture-of-Expert Conformer for Streaming Multilingual ASR
Figure 4 for Mixture-of-Expert Conformer for Streaming Multilingual ASR
Viaarxiv icon

A Deliberation-based Joint Acoustic and Text Decoder

Mar 23, 2023
Sepand Mavandadi, Tara N. Sainath, Ke Hu, Zelin Wu

Figure 1 for A Deliberation-based Joint Acoustic and Text Decoder
Figure 2 for A Deliberation-based Joint Acoustic and Text Decoder
Figure 3 for A Deliberation-based Joint Acoustic and Text Decoder
Figure 4 for A Deliberation-based Joint Acoustic and Text Decoder
Viaarxiv icon

Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages

Mar 03, 2023
Yu Zhang, Wei Han, James Qin, Yongqiang Wang, Ankur Bapna, Zhehuai Chen, Nanxin Chen, Bo Li, Vera Axelrod, Gary Wang, Zhong Meng, Ke Hu, Andrew Rosenberg, Rohit Prabhavalkar, Daniel S. Park, Parisa Haghani, Jason Riesa, Ginger Perng, Hagen Soltau, Trevor Strohman, Bhuvana Ramabhadran, Tara Sainath, Pedro Moreno, Chung-Cheng Chiu, Johan Schalkwyk, Françoise Beaufays, Yonghui Wu

Figure 1 for Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
Figure 2 for Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
Figure 3 for Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
Figure 4 for Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
Viaarxiv icon

Massively Multilingual Shallow Fusion with Large Language Models

Feb 17, 2023
Ke Hu, Tara N. Sainath, Bo Li, Nan Du, Yanping Huang, Andrew M. Dai, Yu Zhang, Rodrigo Cabrera, Zhifeng Chen, Trevor Strohman

Figure 1 for Massively Multilingual Shallow Fusion with Large Language Models
Figure 2 for Massively Multilingual Shallow Fusion with Large Language Models
Figure 3 for Massively Multilingual Shallow Fusion with Large Language Models
Figure 4 for Massively Multilingual Shallow Fusion with Large Language Models
Viaarxiv icon

Scaling Up Deliberation for Multilingual ASR

Oct 11, 2022
Ke Hu, Bo Li, Tara N. Sainath

Figure 1 for Scaling Up Deliberation for Multilingual ASR
Figure 2 for Scaling Up Deliberation for Multilingual ASR
Figure 3 for Scaling Up Deliberation for Multilingual ASR
Figure 4 for Scaling Up Deliberation for Multilingual ASR
Viaarxiv icon

Improving Deliberation by Text-Only and Semi-Supervised Training

Jun 29, 2022
Ke Hu, Tara N. Sainath, Yanzhang He, Rohit Prabhavalkar, Trevor Strohman, Sepand Mavandadi, Weiran Wang

Figure 1 for Improving Deliberation by Text-Only and Semi-Supervised Training
Figure 2 for Improving Deliberation by Text-Only and Semi-Supervised Training
Figure 3 for Improving Deliberation by Text-Only and Semi-Supervised Training
Figure 4 for Improving Deliberation by Text-Only and Semi-Supervised Training
Viaarxiv icon