首页 / 资料库 / 文献详情

Mandarin recognition and improvement based on CTC criterion

ZHANG Limin,WANG Yanzhe,ZHANG Bingqiang,ZHU Nianbin

2019DOAJ (DOAJ: Directory of Open Access Journals)Computer Science被引 1

出版方页面 →

摘要

The cross-entropy criterion of mainstream neural network training classifies and optimizes each frame of acoustic data, while the continuous speech recognition uses the sequence-level transcription accuracy as the performance measurement.For this difference,an end-to-end speech recognition system based on sequence-level transcription is constructed.The phoneme is used as the basic unit to build the model,and the target function of Connectionist Temporal Classification (CTC) is used to improve the structure of Long Short-Term Memory(LSTM) network.The dictionary and language model are introduced in the decoding process,and the tone feature is added to the front end to enrich the acoustic feature.The modeling effect of CTC is improved by using the sequence discrimination training technique.Experimental results show that the recognition efficiency and accuracy of the proposed system is improved,and the Word Error Rate(WER) can be as low as 19.09%±0.16%.

引用本文(GB/T 7714)

ZHANG Limin,WANG Yanzhe,ZHANG Bingqiang,ZHU Nianbin. Mandarin recognition and improvement based on CTC criterion[J]. DOAJ (DOAJ: Directory of Open Access Journals), 2019.

引文网络

参考文献与被引分析加载中…

DOI:https://doi.org/10.19678/j.issn.1000-3428.0051065

本站仅收录题录与摘要供学习参考,全文版权归属出版方;如有侵权请联系我们删除。