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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

SurFit: Learning to Fit Surfaces Improves Few Shot Learning on Point Clouds


Dec 27, 2021
Gopal Sharma, Bidya Dash, Matheus Gadelha, Aruni RoyChowdhury, Marios Loizou, Evangelos Kalogerakis, Liangliang Cao, Erik Learned-Miller, Rui Wang andSubhransu Maji


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Input Length Matters: An Empirical Study Of RNN-T And MWER Training For Long-form Telephony Speech Recognition


Oct 08, 2021
Zhiyun Lu, Yanwei Pan, Thibault Doutre, Liangliang Cao, Rohit Prabhavalkar, Chao Zhang, Trevor Strohman


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition


Oct 07, 2021
Qiujia Li, Yu Zhang, David Qiu, Yanzhang He, Liangliang Cao, Philip C. Woodland

* Submitted to ICASSP 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition


Oct 01, 2021
Yu Zhang, Daniel S. Park, Wei Han, James Qin, Anmol Gulati, Joel Shor, Aren Jansen, Yuanzhong Xu, Yanping Huang, Shibo Wang, Zongwei Zhou, Bo Li, Min Ma, William Chan, Jiahui Yu, Yongqiang Wang, Liangliang Cao, Khe Chai Sim, Bhuvana Ramabhadran, Tara N. Sainath, Françoise Beaufays, Zhifeng Chen, Quoc V. Le, Chung-Cheng Chiu, Ruoming Pang, Yonghui Wu

* 14 pages, 7 figures, 13 tables; v2: minor corrections, reference baselines and bibliography updated 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction


Apr 26, 2021
David Qiu, Yanzhang He, Qiujia Li, Yu Zhang, Liangliang Cao, Ian McGraw

* Submitted to Interspeech 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Bridging the gap between streaming and non-streaming ASR systems bydistilling ensembles of CTC and RNN-T models


Apr 25, 2021
Thibault Doutre, Wei Han, Chung-Cheng Chiu, Ruoming Pang, Olivier Siohan, Liangliang Cao


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models


Apr 06, 2021
Zhiyun Lu, Wei Han, Yu Zhang, Liangliang Cao

* Submitted to INTERSPEECH 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Residual Energy-Based Models for End-to-End Speech Recognition


Mar 25, 2021
Qiujia Li, Yu Zhang, Bo Li, Liangliang Cao, Philip C. Woodland

* Submitted to Interspeech 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Learning Word-Level Confidence For Subword End-to-End ASR


Mar 11, 2021
David Qiu, Qiujia Li, Yanzhang He, Yu Zhang, Bo Li, Liangliang Cao, Rohit Prabhavalkar, Deepti Bhatia, Wei Li, Ke Hu, Tara N. Sainath, Ian McGraw

* To appear in ICASSP 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Spatial-Temporal Alignment Network for Action Recognition and Detection


Dec 04, 2020
Junwei Liang, Liangliang Cao, Xuehan Xiong, Ting Yu, Alexander Hauptmann


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>