A Chinese Text Correction and Intention Identification Method for Speech Interactive Context
作者： Jin Che , Huan Chen , Jing Zeng , Liang-Jie Zhang
DOI: 10.1007/978-3-319-94340-4_10
关键词:
摘要: ASR (Automatic Speech Recognition) is an important technology in man-machine interaction. Due to the complexity of natural language, interference environment and other factors, recognition accuracy has low accuracy. This paper analyzes use cases speech errors proposes a text correction intent method based on phonation principle language characteristics peculiar Chinese, improved edit distance better calculate distance. Through large number experiments, this can improves 22.9% system.
springer.com
sci-hub.st 参考文章(5)
Tomas Mikolov, Greg S. Corrado, Kai Chen, Jeffrey Dean, Efficient Estimation of Word Representations in Vector Space international conference on learning representations. ,(2013)
Ilya Sutskever, Tomas Mikolov, Greg S Corrado, Kai Chen, Jeff Dean, Distributed Representations of Words and Phrases and their Compositionality neural information processing systems. ,vol. 26, pp. 3111- 3119 ,(2013)
Kazuki Fujiwara, Error Correction of Speech Recognition by Custom Phonetic Alphabet Input for Ultra-Small Devices human factors in computing systems. pp. 104- 109 ,(2016) , 10.1145/2851581.2890380
Liu Qingfeng, Phoneme modeling units design for Mandarin LVCSR systems Journal of Tsinghua University. ,(2011)
Youssef Bassil, Mohammad Alwani, Post-Editing Error Correction Algorithm For Speech Recognition using Bing Spelling Suggestion International Journal of Advanced Computer Science and Applications. ,vol. 3, ,(2012) , 10.14569/IJACSA.2012.030217