Adapting self-supervised models to multi-talker speech recognition using speaker embeddings.

Zili Huang Desh Raj Paola García Sanjeev Khudanpur

Published in: CoRR (2022)

Keyphrases

speech recognition
automatic speech recognition
audio visual
speaker recognition
acoustic models
experimental data
model selection
parameter estimation
maximum likelihood
complex systems
d objects
vector space
autoregressive
prior knowledge
feature vectors
bayesian networks
feature selection