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.

arXiv comment4 pages, 2 figures

References in corpus (13)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Attention-Based Models for Speech Recognition
• Sequence Transduction with Recurrent Neural Networks
• A Comparative Study on Transformer vs RNN in Speech Applications
• Online and Linear-Time Attention by Enforcing Monotonic Alignments
• AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale
• Exploring Neural Transducers for End-to-End Speech Recognition
• A Neural Transducer
• Monotonic Chunkwise Attention
• Improving Generalization of Transformer for Speech Recognition with Parallel Schedule Sampling and Relative Positional Embedding
• A comparison of end-to-end models for long-form speech recognition
• Parallel Scheduled Sampling

Cited by in corpus (4)

• Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation
• Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff
• AV Taris: Online Audio-Visual Speech Recognition
• CarneliNet: Neural Mixture Model for Automatic Speech Recognition