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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

GPU-accelerated Guided Source Separation for Meeting Transcription


Dec 10, 2022
Desh Raj, Daniel Povey, Sanjeev Khudanpur

Add code

* 7 pages, 4 figures. Code available at https://github.com/desh2608/gss 

   Access Paper or Ask Questions

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

Fast and parallel decoding for transducer


Oct 31, 2022
Wei Kang, Liyong Guo, Fangjun Kuang, Long Lin, Mingshuang Luo, Zengwei Yao, Xiaoyu Yang, Piotr ┼╗elasko, Daniel Povey

Add code

* Submitted to 2023 IEEE International Conference on Acoustics, Speech and Signal Processing 

   Access Paper or Ask Questions

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

Delay-penalized transducer for low-latency streaming ASR


Oct 31, 2022
Wei Kang, Zengwei Yao, Fangjun Kuang, Liyong Guo, Xiaoyu Yang, Long lin, Piotr ┼╗elasko, Daniel Povey

Add code

* Submitted to 2023 IEEE International Conference on Acoustics, Speech and Signal Processing 

   Access Paper or Ask Questions

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

Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation


Oct 31, 2022
Liyong Guo, Xiaoyu Yang, Quandong Wang, Yuxiang Kong, Zengwei Yao, Fan Cui, Fangjun Kuang, Wei Kang, Long Lin, Mingshuang Luo, Piotr Zelasko, Daniel Povey

Add code

* 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

Pruned RNN-T for fast, memory-efficient ASR training


Jun 23, 2022
Fangjun Kuang, Liyong Guo, Wei Kang, Long Lin, Mingshuang Luo, Zengwei Yao, Daniel Povey

Add code


   Access Paper or Ask Questions

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

Lhotse: a speech data representation library for the modern deep learning ecosystem


Oct 25, 2021
Piotr ┼╗elasko, Daniel Povey, Jan "Yenda" Trmal, Sanjeev Khudanpur

Add code

* Accepted for presentation at NeurIPS 2021 Data-Centric AI (DCAI) Workshop 

   Access Paper or Ask Questions

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

GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio


Jun 13, 2021
Guoguo Chen, Shuzhou Chai, Guanbo Wang, Jiayu Du, Wei-Qiang Zhang, Chao Weng, Dan Su, Daniel Povey, Jan Trmal, Junbo Zhang, Mingjie Jin, Sanjeev Khudanpur, Shinji Watanabe, Shuaijiang Zhao, Wei Zou, Xiangang Li, Xuchen Yao, Yongqing Wang, Yujun Wang, Zhao You, Zhiyong Yan

Add code


   Access Paper or Ask Questions

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

speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment


Apr 03, 2021
Junbo Zhang, Zhiwen Zhang, Yongqing Wang, Zhiyong Yan, Qiong Song, Yukai Huang, Ke Li, Daniel Povey, Yujun Wang

Add code


   Access Paper or Ask Questions

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

An Asynchronous WFST-Based Decoder For Automatic Speech Recognition


Mar 16, 2021
Hang Lv, Zhehuai Chen, Hainan Xu, Daniel Povey, Lei Xie, Sanjeev Khudanpur

Add code

* 5 pages, 5 figures, icassp 

   Access Paper or Ask Questions

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

A Parallelizable Lattice Rescoring Strategy with Neural Language Models


Mar 08, 2021
Ke Li, Daniel Povey, Sanjeev Khudanpur

Add code

* To appear at ICASSP 2021. 5 pages, 1 figure 

   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
>>