Hybrid CTC-Attention based End-to-End Speech Recognition using Subword Units

07/13/2018

∙

by   Zhangyu Xiao, et al.

∙

0

∙

share

In this paper, we present an end-to-end automatic speech recognition system, which successfully employs subword units in a hybrid CTC-Attention based system. The subword units are obtained by the byte-pair encoding (BPE) compression algorithm. Compared to using words as modeling units, using characters or subword units does not suffer from the out-of-vocabulary (OOV) problem. Furthermore, using subword units further offers a capability in modeling longer context than using characters. We evaluate different systems over the LibriSpeech 1000h dataset. The subword-based hybrid CTC-Attention system obtains 6.8 dictionary or external language model. This represents a significant improvement (a 12.8 CTC-Attention system.