CJST: CTC Compressor Based Joint Speech And Text Training For Decoder-only ASR

Abstract

CTC compressor can be an effective approach to integrate audio encoders to decoder-only models, which has gained growing interest for different speech applications. In this work, we propose a novel CTC compressor based joint speech and text training (CJST) framework for decoder-only ASR. CJST matches speech and text modalities from both directions by exploring a simple modality adaptor and several features of the CTC compressor, including sequence compression, on-the-fly forced peaky alignment and CTC class embeddings. Experimental results on the Librispeech and TED-LIUM2 corpora show that the proposed CJST achieves an effective text injection without the need of duration handling, leading to the best performance for both in-domain and cross-domain scenarios. We also provide a comprehensive study on CTC compressor, covering various compression modes, edge case handling and behavior under both clean and noisy data conditions, which reveals the most robust setting to use CTC compressor f

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyzhou2024cjst

Related papers

• Linguistic-enhanced Transformer With CTC Embedding For Speech Recognition (2022)2.26
• Decoder-only Architecture For Speech Recognition With CTC Prompts And Text Data Augmentation (2023)0.00
• Joint Masked CPC And CTC Training For ASR (2020)8.60
• Joint Beam Search Integrating CTC, Attention, And Transducer Decoders (2024)5.24
• CR-CTC: Consistency Regularization On CTC For Improved Speech Recognition (2024)6.30
• Joint Ctc-attention Based End-to-end Speech Recognition Using Multi-task Learning (2016)20.43
• Improved Mask-ctc For Non-autoregressive End-to-end ASR (2020)11.76
• Knn-ctc: Enhancing ASR Via Retrieval Of CTC Pseudo Labels (2023)11.36