Method and apparatus for obtaining transcriptions from multiple training utterances
作者： Jianxiong Wu
DOI: 10.1121/1.429554
关键词: Transcription (linguistics) 、 Computer science 、 Speech recognition 、 Orthography 、 Utterance
摘要: The invention relates to a method and an apparatus for adding new entry speech recognition dictionary, more particularly system generating transcriptions from multiple utterances of given word. novel automatically transcribes several training into without knowledge the orthography word being added. It also provides transcribing single transcription that can be added dictionary. In first step, each utterance is analyzed individually get their respective acoustic characteristics. Following this, these characteristics are combined generate set most likely using information obtained utterances.
harvard.edu
google.gr 参考文章(41)
Abraham N. Daudelin, Directory assistance call processing and calling customer remote signal monitoring arrangements ,(1988)
M. Lennig, Putting speech recognition to work in the telephone network IEEE Computer. ,vol. 23, pp. 35- 41 ,(1990) , 10.1109/2.56869
N. Jain, R. Cole, E. Barnard, Creating speaker-specific phonetic templates with a speaker-independent phonetic recognizer: implications for voice dialing international conference on acoustics speech and signal processing. ,vol. 2, pp. 881- 884 ,(1996) , 10.1109/ICASSP.1996.543262
F. Korkmazskiy, B.-H. Juang, Discriminative training of the pronunciation networks ieee automatic speech recognition and understanding workshop. pp. 223- 229 ,(1997) , 10.1109/ASRU.1997.659009
James K. Baker, Speech recognition apparatus and method Journal of the Acoustical Society of America. ,vol. 88, pp. 1672- 1672 ,(1985) , 10.1121/1.400231
Laurence S Gillick, Robert S Roth, System for processing a succession of utterances spoken in continuous or discrete form The Journal of the Acoustical Society of America. ,vol. 101, pp. 1766- ,(1997) , 10.1121/1.418196
Jed Roberts, James K Baker, Edward W Porter, Method for interactive speech recognition and training Expert Systems With Applications. ,vol. 4, ,(1992) , 10.1016/0957-4174(92)90059-2
Takashi Ariyoshi, Speech recognition method and apparatus Journal of the Acoustical Society of America. ,vol. 94, pp. 1753- 1753 ,(1990) , 10.1121/1.408088
Nick Cremelie, Jean-Pierre Martens, Automatic rule-based generation of word pronunciation networks. conference of the international speech communication association. ,(1997)