A Comparison Of Label-synchronous And Frame-synchronous End-to-end Models For Speech Recognition

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydong2020a

Related papers

• A Comparison Of End-to-end Models For Long-form Speech Recognition (2019)12.93
• Combining Frame-synchronous And Label-synchronous Systems For Speech Recognition (2021)0.00
• Synchronous Transformers For End-to-end Speech Recognition (2019)12.02
• On The Comparison Of Popular End-to-end Models For Large Scale Speech Recognition (2020)0.00
• Label-synchronous Neural Transducer For Adaptable Online E2E Speech Recognition (2023)3.58
• A Comparative Study On Neural Architectures And Training Methods For Japanese Speech Recognition (2021)7.50
• Integration Of Frame- And Label-synchronous Beam Search For Streaming Encoder-decoder Speech Recognition (2023)0.00
• On Comparison Of Encoders For Attention Based End To End Speech Recognition In Standalone And Rescoring Mode (2022)2.26