A practical two-stage training strategy for multi-stream end-to-end
speech recognition

A practical two-stage training strategy for multi-stream end-to-end speech recognition

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019

23 October 2019

Shinji Watanabe

ArXiv (abs)PDF HTML

Papers citing "A practical two-stage training strategy for multi-stream end-to-end speech recognition"

4 / 4 papers shown

Title
Dual-Encoder Architecture with Encoder Selection for Joint Close-Talk and Far-Talk Speech Recognition F. Weninger M. Gaudesi Ralf Leibold R. Gemello P. Zhan 83 4 0 17 Sep 2021
Scaling sparsemax based channel selection for speech recognition with ad-hoc microphone arraysInterspeech (Interspeech), 2021 Junqi Chen Xiao-Lei Zhang 188 11 0 29 Mar 2021
Two-Stage Augmentation and Adaptive CTC Fusion for Improved Robustness of Multi-Stream End-to-End ASRSpoken Language Technology Workshop (SLT), 2021 Ruizhi Li Gregory Sell H. Hermansky 119 2 0 05 Feb 2021
Multi-stream Convolutional Neural Network with Frequency Selection for Robust Speaker VerificationComputing and informatics (CAI), 2020 Wei Yao Shen Chen Jiamin Cui Yaolin Lou 197 7 0 21 Dec 2020