Blank Collapse: Compressing CTC emission for the faster decoding
This work addresses the problem of slow decoding speeds in automatic speech recognition systems, offering a practical improvement for real-time applications, though it is incremental as it optimizes an existing method.
The paper tackles the computational inefficiency of CTC beam search decoding in speech recognition by analyzing the blank label and proposing a simple method to reduce calculations, achieving up to 78% faster decoding speed with minimal accuracy loss on LibriSpeech datasets.
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.