A Temporal Alignment Buffer with minimum-KL delay selection lets Delayed-KD reach 5.42% CER on AISHELL-1 at 40 ms latency, matching U2++ at 320 ms.
Dataset We conduct experiments on two Mandarin Chinese datasets: AISHELL-1 [22] (178 hours) and the large-scale, multi-domain WenetSpeech [24] (10,000 hours)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Delayed-KD: Delayed Knowledge Distillation based CTC for Low-Latency Streaming ASR
A Temporal Alignment Buffer with minimum-KL delay selection lets Delayed-KD reach 5.42% CER on AISHELL-1 at 40 ms latency, matching U2++ at 320 ms.