A Mamba-based state-space ASR model and four fine-tuned self-supervised models achieve claimed state-of-the-art word error rates on whispered and normal speech across three English dialects, including near-perfect results on wTIMIT and CHAINS.
These challenges can severely degrade the performance of traditional systems, highlighting the necessity of developing ASR models specifically tailored to handle whispered speech
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
State-Space Models in Efficient Whispered and Multi-dialect Speech Recognition
A Mamba-based state-space ASR model and four fine-tuned self-supervised models achieve claimed state-of-the-art word error rates on whispered and normal speech across three English dialects, including near-perfect results on wTIMIT and CHAINS.