Joint Masked CPC And CTC Training For ASR

Abstract

Self-supervised learning (SSL) has shown promise in learning representations of audio that are useful for automatic speech recognition (ASR). But, training SSL models like wav2vec~2.0 requires a two-stage pipeline. In this paper we demonstrate a single-stage training of ASR models that can utilize both unlabeled and labeled data. During training, we alternately minimize two losses: an unsupervised masked Contrastive Predictive Coding (CPC) loss and the supervised audio-to-text alignment loss Connectionist Temporal Classification (CTC). We show that this joint training method directly optimizes performance for the downstream ASR task using unsupervised data while achieving similar word error rates to wav2vec~2.0 on the Librispeech 100-hour dataset. Finally, we postulate that solving the contrastive task is a regularization for the supervised CTC loss.

Stats

• citations13
• S2 citations—
• github stars0
• HF likes0
• heat score8.60
• arxiv keytalnikar2020joint

Related papers

• Improved Mask-ctc For Non-autoregressive End-to-end ASR (2020)11.76
• Efficient Infusion Of Self-supervised Representations In Automatic Speech Recognition (2024)0.00
• Guided Contrastive Self-supervised Pre-training For Automatic Speech Recognition (2022)0.00
• CJST: CTC Compressor Based Joint Speech And Text Training For Decoder-only ASR (2024)3.58
• Multilingual Training And Cross-lingual Adaptation On Ctc-based Acoustic Model (2017)0.00
• Masked Pre-trained Encoder Base On Joint Ctc-transformer (2020)0.00
• Multi-variant Consistency Based Self-supervised Learning For Robust Automatic Speech Recognition (2021)0.00
• Non-autoregressive Error Correction For Ctc-based ASR With Phone-conditioned Masked LM (2022)5.84