Chunkwise Aligner matches Transducer accuracy in streaming ASR while improving training and decoding efficiency by chunking audio and aligning to leftmost frames with end-of-chunk probabilities.
Hybrid CTC/Attention Architecture for End-to-End 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
-
Chunkwise Aligners for Streaming Speech Recognition
Chunkwise Aligner matches Transducer accuracy in streaming ASR while improving training and decoding efficiency by chunking audio and aligning to leftmost frames with end-of-chunk probabilities.