KLD-based speaker adaptation of seq2seq ASR achieves 25% relative WER reduction, outperforming the 18.7% gain from conventional acoustic model adaptation.
Sequence-to-sequence (seq2seq) modeling [4, 5] is a state-of-the-art method for end-to-end ASR, which has shown competitive results compared to traditional ASR systems [6]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR
KLD-based speaker adaptation of seq2seq ASR achieves 25% relative WER reduction, outperforming the 18.7% gain from conventional acoustic model adaptation.