CR-CTC: Consistency Regularization On CTC For Improved Speech Recognition

Abstract

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 effec

Stats

• citations0
• S2 citations—
• github stars1406
• HF likes0
• heat score6.30
• arxiv keyyao2024cr

Related papers

• Adamer-ctc: Connectionist Temporal Classification With Adaptive Maximum Entropy Regularization For Automatic Speech Recognition (2024)5.84
• BERT Meets CTC: New Formulation Of End-to-end Speech Recognition With Pre-trained Masked Language Model (2022)0.00
• Residual Convolutional CTC Networks For Automatic Speech Recognition (2017)0.00
• Improved Mask-ctc For Non-autoregressive End-to-end ASR (2020)11.76
• Multitask Learning With CTC And Segmental CRF For Speech Recognition (2017)0.00
• Knn-ctc: Enhancing ASR Via Retrieval Of CTC Pseudo Labels (2023)11.36
• Efficient CTC Regularization Via Coarse Labels For End-to-end Speech Translation (2023)0.00
• Non-autoregressive Error Correction For Ctc-based ASR With Phone-conditioned Masked LM (2022)5.84