An on-line incremental speaker adaptation technique for audio stream transcription.

Diego Giuliani Fabio Brugnara

Published in: INTERSPEECH (2013)

Keyphrases

audio stream
speaker adaptation
speech recognition
maximum likelihood
speaker diarization
video streams
acoustic features
speech recognition systems
neural network
automatic speech recognition
speech recognizer
image processing
video sequences
information retrieval systems
multi modal
unsupervised learning