DQ-Data2vec adds online K-means quantizers with cluster counts matched to language and phoneme counts to decouple these features during multilingual speech pre-training, improving phoneme and word error rates on CommonVoice.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DQ-Data2vec: Decoupling Quantization for Multilingual Speech Recognition
DQ-Data2vec adds online K-means quantizers with cluster counts matched to language and phoneme counts to decouple these features during multilingual speech pre-training, improving phoneme and word error rates on CommonVoice.