A comparable study of modeling units for end-to-end Mandarin speech recognition

Abstract

End-To-End speech recognition have become increasingly popular in mandarin speech recognition and achieved delightful performance. Mandarin is a tonal language which is different from English and requires special treatment for the acoustic modeling units. There have been several different kinds of modeling units for mandarin such as phoneme, syllable and Chinese character. In this work, we explore two major end-to-end models: connectionist temporal classification (CTC) model and attention based encoder-decoder model for mandarin speech recognition. We compare the performance of three different scaled modeling units: context dependent phoneme(CDP), syllable with tone and Chinese character. We find that all types of modeling units can achieve approximate character error rate (CER) in CTC model and the performance of Chinese character attention model is better than syllable attention model. Furthermore, we find that Chinese character is a reasonable unit for mandarin speech recognition. On DidiCallcenter task, Chinese character attention model achieves a CER of 5.68% and CTC model gets a CER of 7.29%, on the other DidiReading task, CER are 4.89% and 5.79%, respectively. Moreover, attention model achieves a better performance than CTC model on both datasets.

arXiv comment5 pages

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Deep Learning in Neural Networks: An Overview
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding
• Sequence-to-Sequence Learning as Beam-Search Optimization
• Towards better decoding and language model integration in sequence to sequence models

Cited by in corpus (5)

• Towards End-to-End Code-Switching Speech Recognition
• A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese
• Research on Modeling Units of Transformer Transducer for Mandarin Speech Recognition
• DiDiSpeech: A Large Scale Mandarin Speech Corpus
• Exploring Lexicon-Free Modeling Units for End-to-End Korean and Korean-English Code-Switching Speech Recognition