Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition

11 January 2022

Papers citing "Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition"

3 / 3 papers shown

Title
Streaming Target-Speaker ASR with Neural Transducer Takafumi Moriya Hiroshi Sato Tsubasa Ochiai Marc Delcroix T. Shinozaki 26 21 0 09 Sep 2022
Mask scalar prediction for improving robust automatic speech recognition A. Narayanan James Walker S. Panchapagesan N. Howard Yuma Koizumi 11 4 0 26 Apr 2022
Deep Extractor Network for Target Speaker Recovery From Single Channel Speech Mixtures J. Wang Jie Chen Dan Su Lianwu Chen Meng Yu Y. Qian Dong Yu 38 90 0 24 Jul 2018