Method for correcting error characters in results of speech recognition and speech recognition system using the same
作者： Donald T. Tang , Hui Su , Qian Ying Wang , Li Qin Shen , Yong Qin
DOI:
关键词:
摘要: The invention discloses a method for correcting one or more error characters in results of speech recognition, the comprising steps of: marking recognition results; inputting correct corresponding to marked by input based on character-shape; recognizing displaying candidate characters; selecting desired from accordance with user; and replacing selected characterized further step filtering acoustic information associated characters.
lens.org 参考文章(7)
Sean Kenneth Maxted, Pen based edit correction interface method and apparatus ,(1999)
Masayuki Kimura, Image recognition apparatus and method for recognizing a pattern within an image ,(1989)
Larry S. Yaeger, Method for training an adaptive statistical classifier to discriminate against inproper patterns ,(1995)
Angshuman Guha, James A. Pittman, Patrick M. Haluptzok, Handwriting and speech recognizer using neural network with separate start and continuation output scores ,(1999)
Philip A. Chou, Leslie T. Niles, Gary E. Kopec, Method and system for automatic transcription correction ,(1996)
Hsin-min Wang, Tai-Hsuan Ho, Rung-Chiung Yang, Jia-Lin Shen, Bo-Ren Bai, Jenn-Chau Hong, Wei-Peng Chen, Tong-Lo Yu, Lin-Shan Lee, None, Complete recognition of continuous Mandarin speech for Chinese language with very large vocabulary using limited training data IEEE Transactions on Speech and Audio Processing. ,vol. 5, pp. 195- 200 ,(1997) , 10.1109/89.554782
Kae-Cherng Yang, Tai-Hsuan Ho, Lee-Feng Chienq, Lin-Shan Lee, Statistics-based segment pattern lexicon-a new direction for Chinese language modeling international conference on acoustics speech and signal processing. ,vol. 1, pp. 169- 172 ,(1998) , 10.1109/ICASSP.1998.674394