Papers › CR-CTC: Consistency regularization on CTC for improved speech recognition

CR-CTC: Consistency regularization on CTC for improved speech recognition

7 Oct 2024arXiv:2410.05101archive 2025-07-28

Zengwei Yao, Wei Kang, Xiaoyu Yang, Fangjun Kuang, Liyong Guo, Han Zhu, Zengrui Jin, Zhaoqing Li, Long Lin, Daniel Povey

Connectionist Temporal Classification (CTC) is a widely used method for automatic speech recognition (ASR), renowned for its simplicity and computational efficiency. However, it often falls short in recognition performance. In this work, we propose the Consistency-Regularized CTC (CR-CTC), which enforces consistency between two CTC distributions obtained from different augmented views of the input speech mel-spectrogram. We provide in-depth insights into its essential behaviors from three perspectives: 1) it conducts self-distillation between random pairs of sub-models that process different augmented views; 2) it learns contextual representation through masked prediction for positions within time-masked regions, especially when we increase the amount of time masking; 3) it suppresses the extremely peaky CTC distributions, thereby reducing overfitting and improving the generalization ability. Extensive experiments on LibriSpeech, Aishell-1, and GigaSpeech datasets demonstrate the effectiveness of our CR-CTC. It significantly improves the CTC performance, achieving state-of-the-art results comparable to those attained by transducer or systems combining CTC and attention-based encoder-decoder (CTC/AED). We release our code at https://github.com/k2-fsa/icefall.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

k2-fsa/icefall officialmentioned in paperpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unifying Streaming and Non-streaming Zipformer-based ASR (arXiv:2506.14434; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Computational EfficiencyDecoderSpeech Recognitionspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Recognition AISHELL-1 Zipformer+CR-CTC (no external language model) Params(M) 66.2 #6 of 18 Archive leaderboard report
Speech Recognition AISHELL-1 Zipformer+CR-CTC (no external language model) Word Error Rate (WER) 4.02 #6 of 18 Archive leaderboard report
Speech Recognition GigaSpeech DEV Zipformer+pruned transducer w/ CR-CTC (no external language model) Word Error Rate (WER) 9.95 #2 of 5 Archive leaderboard report
Speech Recognition GigaSpeech DEV Zipformer+pruned transducer (no external language model) Word Error Rate (WER) 10.09 #3 of 5 Archive leaderboard report
Speech Recognition GigaSpeech DEV Zipformer+CR-CTC (no external language model) Word Error Rate (WER) 10.15 #4 of 5 Archive leaderboard report
Speech Recognition GigaSpeech TEST Zipformer+pruned transducer w/ CR-CTC (no external language model) Word Error Rate (WER) 10.03 #1 of 5 Archive leaderboard report
Speech Recognition GigaSpeech TEST Zipformer+CR-CTC/AED (no external language model) Word Error Rate (WER) 10.07 #2 of 5 Archive leaderboard report
Speech Recognition GigaSpeech TEST Zipformer+pruned transducer (no external language model) Word Error Rate (WER) 10.2 #3 of 5 Archive leaderboard report
Speech Recognition GigaSpeech TEST Zipformer+CR-CTC (no external language model) Word Error Rate (WER) 10.28 #4 of 5 Archive leaderboard report
Speech Recognition LibriSpeech test-clean Zipformer+pruned transducer w/ CR-CTC (no external language model) Word Error Rate (WER) 1.88 #16 of 64 Archive leaderboard report
Speech Recognition LibriSpeech test-clean Zipformer+CR-CTC (no external language model) Word Error Rate (WER) 2.02 #26 of 64 Archive leaderboard report
Speech Recognition LibriSpeech test-other Zipformer+pruned transducer w/ CR-CTC (no external language model) Word Error Rate (WER) 3.95 #15 of 53 Archive leaderboard report
Speech Recognition LibriSpeech test-other Zipformer+CR-CTC (no external language model) Word Error Rate (WER) 4.35 #24 of 53 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections