Improving Multi-Speaker ASR With Overlap-Aware Encoding And Monotonic Attention.

Tao Li Feng Wang Wenhao Guan Lingyan Huang Qingyang Hong Lin Li

Published in: ICASSP (2024)

Keyphrases

automatic speech recognition
speech recognition
speech signal
anti monotonic
focus of attention
database
real time
machine learning
search engine
pattern recognition
hidden markov models
audio visual
noisy environments
speaker recognition
speaker diarization