CTC-seeded variable-length edit refinement with a diffusion-based Edit Flow decoder achieves WER reductions in non-autoregressive ASR using only two inference steps plus classifier-free guidance.
Deliberation of stream- ing rnn-transducer by non-autoregressive decoding,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 2roles
background 1polarities
unclear 1representative citing papers
A survey that classifies non-intrusive ASR refinement methods into five categories, reviews domain adaptation and evaluation datasets, proposes standardized metrics, and identifies future research directions.
citing papers explorer
-
CTC-Seeded Token Edit Refinement for Non-Autoregressive Speech Recognition
CTC-seeded variable-length edit refinement with a diffusion-based Edit Flow decoder achieves WER reductions in non-autoregressive ASR using only two inference steps plus classifier-free guidance.
-
Non-Intrusive Automatic Speech Recognition Refinement: A Survey
A survey that classifies non-intrusive ASR refinement methods into five categories, reviews domain adaptation and evaluation datasets, proposes standardized metrics, and identifies future research directions.