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.
Chunkwise Aligners for Streaming Speech Recognition
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
We propose the Chunkwise Aligner, a novel architecture for streaming automatic speech recognition (ASR). While the Transducer is the standard model for streaming ASR, its training is costly due to the need to compute all possible audio-label alignments. The recently introduced Aligner reduces this cost by discarding explicit alignments, but this modification makes it unsuitable for streaming. Our approach overcomes this limitation by dividing the audio into chunks and aligning each label to the leftmost frames of its chunk, whereas transitions between chunks are managed by a learned end-of-chunk probability. Experiments show that the Chunkwise Aligner not only matches the Transducer's accuracy in both offline and streaming scenarios, but also offers superior training and decoding efficiencies.
citation-role summary
citation-polarity summary
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 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.