System and method for providing a compensated speech recognition model for speech recognition
作者： Richard C Rose , Sarangarajan Pathasarathy , Aaron Edward Rosenberg , Shrikanth Sambasivan Narayanan , None
DOI:
关键词:
摘要: An automatic speech recognition (ASR) system and method is provided for controlling the of utterances generated by an end user operating a communications device. The ASR can be used with device that in network. input into mobile device, to perform compensating techniques using at least one characteristic updating recognizer associated determined background noise value distortion based on features augment limited data capability example, caused devices physically located
google.com.mx 参考文章(34)
Anthony S Ranzino, Communication and location system for shopping malls, parks, business districts, and the like ,(1999)
Yasuhiro Komori, Hiroki Yamamoto, Speech processing apparatus and method using a noise-adaptive PMC model ,(1997)
Juinn-Yan Chen, James Pan, Josephine Chang, Yoon Kim, Spelling speech recognition apparatus and method for communications ,(2000)
Alan Lawrence Higgins, Jack E. Porter, Steven F. Boll, Noise suppression and channel equalization preprocessor for speech and speaker recognizers: method and apparatus ,(1998)
Craig Alexander Will, Call-forwarding system using adaptive model of user behavior ,(1998)
Shigeki Sagayama, Yoshikazu Yamaguchi, Jun-Ichi Takahashi, Satoshi Takahashi, Scheme for model adaptation in pattern recognition based on Taylor expansion ASAJ. ,vol. 108, pp. 1987- ,(1997)
Charles Calvin Byers, Enhanced automatic speech recognition using multiple directional microphones ,(1999)
Ben Shahshahani, Remco Teunen, Voice processing and verification system ,(1998)
Stephen Austin, Sreeram Balakrishnan, Context dependent phoneme networks for encoding speech information Journal of the Acoustical Society of America. ,vol. 110, pp. 1248- ,(1998)
Louis D. Finkelstein, Eugene J. Bruckert, Daniel P. Brown, System and method for securing speech transactions ,(1998)