A Comparison of Label-Synchronous and Frame-Synchronous End-to-End Models for Speech Recognition
This work provides insights for researchers and practitioners in speech recognition by systematically comparing two model types, but it is incremental as it focuses on existing paradigms without introducing new methods.
The paper compared label-synchronous (transformer) and frame-synchronous (CIF-based) end-to-end speech recognition models, finding that each has advantages consistent with their synchronous modes across three public datasets and a large-scale 12,000-hour dataset.
End-to-end models are gaining wider attention in the field of automatic speech recognition (ASR). One of their advantages is the simplicity of building that directly recognizes the speech frame sequence into the text label sequence by neural networks. According to the driving end in the recognition process, end-to-end ASR models could be categorized into two types: label-synchronous and frame-synchronous, each of which has unique model behaviour and characteristic. In this work, we make a detailed comparison on a representative label-synchronous model (transformer) and a soft frame-synchronous model (continuous integrate-and-fire (CIF) based model). The results on three public dataset and a large-scale dataset with 12000 hours of training data show that the two types of models have respective advantages that are consistent with their synchronous mode.