HASRD factorizes SSL speech representations into a first semantic codebook and residual acoustic codebooks, reporting improved ASR and reconstruction at 3.1 kbps versus SpeechTokenizer's 6.0 kbps.
For acoustic training, we adopt the DAC framework [16], extracting random 5-second segments (vs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
HASRD: Hierarchical Acoustic and Semantic Representation Disentanglement
HASRD factorizes SSL speech representations into a first semantic codebook and residual acoustic codebooks, reporting improved ASR and reconstruction at 3.1 kbps versus SpeechTokenizer's 6.0 kbps.