Awni Hannun

Speech Recognition

This research focuses on more accurate speech recognition with end-to-end models and scale. In the past I also worked on hybrid HMM-based speech recognition.

Selected Publications
  • Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters Vineel Pratap, Anuroop Sriram, Paden Tomasello, Awni Hannun, Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert. Interspeech 2020. (paper)
  • Scaling up online speech recognition using convnets, Vineel Pratap, Qiantong Xu, Jacob Kahn, Gilad Avidov, Tatiana Likhomanenko, Awni Hannun, Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert. Interspeech 2020. (paper)
  • Word-level Speech Recognition with a Letter to Word Encoder Ronan Collobert, Awni Hannun, Gabriel Synnaeve. ICML 2020. (paper)
  • Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition Adrien Dufraux, Emmanuel Vincent, Awni Hannun, Armelle Brun, Matthijs Douze. ASRU 2019. (paper)
  • Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions, Awni Hannun, Ann Lee, Qiantong Xu, Ronan Collobert. Interspeech 2019. (paper, code)
  • Wav2Letter++: A Fast Open-source Speech Recognition System,Vineel Pratap, Awni Hannun, Qiantong Xu, Jeff Cai, Jacob Kahn, Gabriel Synnaeve, Vitaliy Liptchinsky, Ronan Collobert. ICASSP 2019. (paper, code, blog)
  • Deep Speech 2: End-to-End Speech Recognition in English and Mandarin, SVAIL. ICML 2016. (pdf, long)
    Mentions: MIT Tech Review, MIT Tech Review
  • Deep Speech: Scaling up end-to-end speech recognition, Awni Y. Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan Prenger, Sanjeev Satheesh, Shubho Sengupta, Adam Coates, Andrew Y. Ng. arXiv:1412.5567, 2014. (pdf)
    Mentions: Forbes
  • Rectifier Nonlinearities Improve Neural Network Acoustic Models, Andrew L. Maas, Awni Y. Hannun, and Andrew Y. Ng. ICML Workshop on Deep Learning for Audio, Speech, and Language Processing (WDLASL 2013). (pdf)