Blank Collapse: Compressing CTC Emission For The Faster Decoding

Abstract

Connectionist Temporal Classification (CTC) model is a very efficient method for modeling sequences, especially for speech data. In order to use CTC model as an Automatic Speech Recognition (ASR) task, the beam search decoding with an external language model like n-gram LM is necessary to obtain reasonable results. In this paper we analyze the blank label in CTC beam search deeply and propose a very simple method to reduce the amount of calculation resulting in faster beam search decoding speed. With this method, we can get up to 78% faster decoding speed than ordinary beam search decoding with a very small loss of accuracy in LibriSpeech datasets. We prove this method is effective not only practically by experiments but also theoretically by mathematical reasoning. We also observe that this reduction is more obvious if the accuracy of the model is higher.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyjung2022blank

Related papers

• Adding Connectionist Temporal Summarization Into Conformer To Improve Its Decoder Efficiency For Speech Recognition (2022)0.00
• Comparison Of Decoding Strategies For CTC Acoustic Models (2017)10.48
• CTC Blank Triggered Dynamic Layer-skipping For Efficient Ctc-based Speech Recognition (2024)0.00
• Non-autoregressive Error Correction For Ctc-based ASR With Phone-conditioned Masked LM (2022)5.84
• Efficient CTC Regularization Via Coarse Labels For End-to-end Speech Translation (2023)0.00
• CR-CTC: Consistency Regularization On CTC For Improved Speech Recognition (2024)6.30
• Back From The Future: Bidirectional CTC Decoding Using Future Information In Speech Recognition (2021)0.00
• Knn-ctc: Enhancing ASR Via Retrieval Of CTC Pseudo Labels (2023)11.36