Login / Signup
Extracting Speaker and Emotion Information from Self-Supervised Speech Models via Channel-Wise Correlations.
Themos Stafylakis
Ladislav Mosner
Sofoklis Kakouros
Oldrich Plchot
Lukás Burget
Jan Cernocký
Published in:
SLT (2022)
Keyphrases
</>
speech recognition
prior knowledge
domain knowledge
model selection
information sources
contextual information
historical data
user interaction
information processing
information fusion
search engine
information extraction
information content
speaker recognition