Simultaneous ensemble teacher update with the student model improves unsupervised domain adaptation for ASR, reducing WER by 4.6% on the Switchboard eval00 set.
Recent advances in end-to-end automatic speech recognition,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Teaching the Teachers: Boosting unsupervised domain adaptation in speech recognition by ensemble update
Simultaneous ensemble teacher update with the student model improves unsupervised domain adaptation for ASR, reducing WER by 4.6% on the Switchboard eval00 set.