Speaker Embeddings Incorporating Acoustic Conditions for Diarization.

Yosuke Higuchi Masayuki Suzuki Gakuto Kurata

Published in: ICASSP (2020)

Keyphrases

speaker diarization
speaker identification
sufficient conditions
acoustic features
speech recognition
mel frequency cepstral coefficients
environmental conditions
prosodic features
multimedia
high dimensional
manifold learning
source localization
speech sounds