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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities


Nov 10, 2022
Andros Tjandra, Nayan Singhal, David Zhang, Ozlem Kalinli, Abdelrahman Mohamed, Duc Le, Michael L. Seltzer

Add code

* Submitted to ICASSP 2023 

   Access Paper or Ask Questions

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

Biased Self-supervised learning for ASR


Nov 04, 2022
Florian L. Kreyssig, Yangyang Shi, Jinxi Guo, Leda Sari, Abdelrahman Mohamed, Philip C. Woodland

Add code

* Submitted to ICASSP 2023 

   Access Paper or Ask Questions

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

SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning


Oct 16, 2022
Tzu-hsun Feng, Annie Dong, Ching-Feng Yeh, Shu-wen Yang, Tzu-Quan Lin, Jiatong Shi, Kai-Wei Chang, Zili Huang, Haibin Wu, Xuankai Chang, Shinji Watanabe, Abdelrahman Mohamed, Shang-Wen Li, Hung-yi Lee

Add code

* Accepted by 2022 SLT Workshop 

   Access Paper or Ask Questions

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

$\textrm{D}^3\textrm{Former}$: Debiased Dual Distilled Transformer for Incremental Learning


Jul 25, 2022
Abdelrahman Mohamed, Rushali Grandhe, KJ Joseph, Salman Khan, Fahad Khan

Add code

* Code is available at https://tinyurl.com/d3former 

   Access Paper or Ask Questions

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

DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon


Jun 22, 2022
Robin Algayres, Tristan Ricoul, Julien Karadayi, Hugo Laurençon, Salah Zaiem, Abdelrahman Mohamed, Benoît Sagot, Emmanuel Dupoux

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

LegoNN: Building Modular Encoder-Decoder Models


Jun 07, 2022
Siddharth Dalmia, Dmytro Okhonko, Mike Lewis, Sergey Edunov, Shinji Watanabe, Florian Metze, Luke Zettlemoyer, Abdelrahman Mohamed

Add code

* 13 pages; Submitted to TASLP 2022 

   Access Paper or Ask Questions

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

Self-Supervised Speech Representation Learning: A Review


May 21, 2022
Abdelrahman Mohamed, Hung-yi Lee, Lasse Borgholt, Jakob D. Havtorn, Joakim Edin, Christian Igel, Katrin Kirchhoff, Shang-Wen Li, Karen Livescu, Lars Maaløe, Tara N. Sainath, Shinji Watanabe

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

Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT


May 15, 2022
Bowen Shi, Abdelrahman Mohamed, Wei-Ning Hsu

Add code

* Submitted to Interspeech 

   Access Paper or Ask Questions

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

Unified Speech-Text Pre-training for Speech Translation and Recognition


Apr 11, 2022
Yun Tang, Hongyu Gong, Ning Dong, Changhan Wang, Wei-Ning Hsu, Jiatao Gu, Alexei Baevski, Xian Li, Abdelrahman Mohamed, Michael Auli, Juan Pino

Add code

* ACL 2022 main conference 

   Access Paper or Ask Questions

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

Federated Learning with Partial Model Personalization


Apr 08, 2022
Krishna Pillutla, Kshitiz Malik, Abdelrahman Mohamed, Michael Rabbat, Maziar Sanjabi, Lin Xiao

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
1
2
3
4
5
>>