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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization


Jun 16, 2022
Andrea Fasoli, Chia-Yu Chen, Mauricio Serrano, Swagath Venkataramani, George Saon, Xiaodong Cui, Brian Kingsbury, Kailash Gopalakrishnan

* 5 pages, 2 figures, 1 table. Paper accepted to Interspeech 2022 

   Access Paper or Ask Questions

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

Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing


Mar 29, 2022
Xiaodong Cui, George Saon, Tohru Nagano, Masayuki Suzuki, Takashi Fukuda, Brian Kingsbury, Gakuto Kurata

* Submitted to Interspeech 2022 

   Access Paper or Ask Questions

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

Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent


Dec 02, 2021
Wei Zhang, Mingrui Liu, Yu Feng, Xiaodong Cui, Brian Kingsbury, Yuhai Tu


   Access Paper or Ask Questions

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

Asynchronous Decentralized Distributed Training of Acoustic Models


Oct 21, 2021
Xiaodong Cui, Wei Zhang, Abdullah Kayi, Mingrui Liu, Ulrich Finkler, Brian Kingsbury, George Saon, David Kung

* Accepted by IEEE/ACM Transactions on Audio, Speech and Language Processing 

   Access Paper or Ask Questions

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

4-bit Quantization of LSTM-based Speech Recognition Models


Aug 27, 2021
Andrea Fasoli, Chia-Yu Chen, Mauricio Serrano, Xiao Sun, Naigang Wang, Swagath Venkataramani, George Saon, Xiaodong Cui, Brian Kingsbury, Wei Zhang, Zoltán Tüske, Kailash Gopalakrishnan

* 5 pages, 3 figures, Andrea Fasoli and Chia-Yu Chen equally contributed to this work. Paper accepted 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

Reducing Exposure Bias in Training Recurrent Neural Network Transducers


Aug 24, 2021
Xiaodong Cui, Brian Kingsbury, George Saon, David Haws, Zoltan Tuske

* accepted 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

On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation


Jun 09, 2021
Wei Zhang, Ziming Huang, Yada Zhu, Guangnan Ye, Xiaodong Cui, Fan Zhang

* 13 pages; Accepted to ACL 2021 

   Access Paper or Ask Questions

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

ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training


Apr 21, 2021
Chia-Yu Chen, Jiamin Ni, Songtao Lu, Xiaodong Cui, Pin-Yu Chen, Xiao Sun, Naigang Wang, Swagath Venkataramani, Vijayalakshmi Srinivasan, Wei Zhang, Kailash Gopalakrishnan

* NeurIPS2020 accepted https://proceedings.neurips.cc/paper/2020/hash/9d58963592071dbf38a0fa114269959c-Abstract.html 

   Access Paper or Ask Questions

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

Federated Acoustic Modeling For Automatic Speech Recognition


Feb 08, 2021
Xiaodong Cui, Songtao Lu, Brian Kingsbury

* Accepted by 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

Speech Emotion Recognition with Multiscale Area Attention and Data Augmentation


Feb 03, 2021
Mingke Xu, Fan Zhang, Xiaodong Cui, Wei Zhang

* Accepted by 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
1
2
3
>>