InterSpeech 2021

Neural network training methods for ASR

Towards Lifelong Learning of End-to-end ASR
(3 minutes introduction)

Heng-Jui Chang (National Taiwan University, Taiwan), Hung-yi Lee (National Taiwan University, Taiwan), Lin-shan Lee (National Taiwan University, Taiwan)

Towards Lifelong Learning of End-to-end ASR
(longer introduction)

Heng-Jui Chang (National Taiwan University, Taiwan), Hung-yi Lee (National Taiwan University, Taiwan), Lin-shan Lee (National Taiwan University, Taiwan)

Regularizing Word Segmentation by Creating Misspellings
(3 minutes introduction)

Hainan Xu (Google, USA), Kartik Audhkhasi (Google, USA), Yinghui Huang (Google, USA), Jesse Emond (Google, USA), Bhuvana Ramabhadran (Google, USA)

Multitask Training with Text Data for End-to-End Speech Recognition
(3 minutes introduction)

Peidong Wang (Google, USA), Tara N. Sainath (Google, USA), Ron J. Weiss (Google, USA)

Emitting Word Timings with HMM-free End-to-End System in Automatic Speech Recognition
(3 minutes introduction)

Xianzhao Chen (Tianjin University, China), Hao Ni (ByteDance, China), Yi He (ByteDance, China), Kang Wang (ByteDance, China), Zejun Ma (ByteDance, China), Zongxia Xie (Tianjin University, China)

4-bit Quantization of LSTM-based Speech Recognition Models
(3 minutes introduction)

Andrea Fasoli (IBM, USA), Chia-Yu Chen (IBM, USA), Mauricio Serrano (IBM, USA), Xiao Sun (IBM, USA), Naigang Wang (IBM, USA), Swagath Venkataramani (IBM, USA), George Saon (IBM, USA), Xiaodong Cui (IBM, USA), Brian Kingsbury (IBM, USA), Wei Zhang (IBM, USA), Zoltán Tüske (IBM, USA), Kailash Gopalakrishnan (IBM, USA)

4-bit Quantization of LSTM-based Speech Recognition Models
(longer introduction)

Andrea Fasoli (IBM, USA), Chia-Yu Chen (IBM, USA), Mauricio Serrano (IBM, USA), Xiao Sun (IBM, USA), Naigang Wang (IBM, USA), Swagath Venkataramani (IBM, USA), George Saon (IBM, USA), Xiaodong Cui (IBM, USA), Brian Kingsbury (IBM, USA), Wei Zhang (IBM, USA), Zoltán Tüske (IBM, USA), Kailash Gopalakrishnan (IBM, USA)