On the Disentanglement and Robustness of Self-Supervised Speech Representations.

Yanjue Song Doyeon Kim Nilesh Madhu Hong-Goo Kang

Published in: ICEIC (2024)

Keyphrases

speech recognition
speech signal
hidden markov models
audio visual
computational efficiency
speaker recognition
text to speech
decision trees
automatic speech recognition
audio features
spoken language
high robustness
recognition engine
endpoint detection