Method and system for automatically determining phonetic transciptions associated with spelled words
作者： Jean-Claude Junqua , Roland Kuhn , Matteo Contolini
DOI:
关键词: Natural language processing 、 Morpheme 、 User input 、 Transcription (linguistics) 、 Artificial intelligence 、 Automatic speech 、 Lexicon 、 Speech recognition 、 Computer science
摘要: New entries are added to the lexicon by entering them as spelled words. A transcription generator, such a decision-tree-based phoneme or morpheme converts each word into set of n-best transcriptions sequences. Meanwhile, user input automatically generated speech corresponding is processed an automatic recognizer and rescores sequences produced generator. One more highest scored (highest confidence) may be update it. If desired, word-pronunciation pairs system can used retrain making adaptive self-learning.
google.co.in 参考文章(16)
Edward Komissarchik, Julia Komissarchik, Andrey Ivanov, Alexander Rozanov, Mikhail Kronrod, Nina Zinovieva, Dimitri Bogdanov, Jacob Kaminsky, Olga Krivnova, Maxim Paklin, Mikhail Malkovsky, Vladimir Segal, Yuri Finkelstein, Vladimir Arlazarov, Knowledge-based speech recognition system and methods having frame length computed based upon estimated pitch period of vocalic intervals ,(1995)
Alexander Waibel, Arthur McNair, Bernhard Suhm, Method and apparatus for correcting and repairing machine-transcribed input using independent or cross-modal secondary input ,(1996)
Dimitri Kanevsky, Wlodek Wlodzimierz Zadrozny, Training speech recognition by matching audio segment frequency of occurrence with frequency of words and letter combinations in a corpus ASAJ. ,vol. 108, pp. 1383- ,(1998)
Enrico L. Boccherieri, Automatic speech recognizer Journal of the Acoustical Society of America. ,vol. 97, pp. 3224- 3224 ,(1993) , 10.1121/1.411761
Eduardo Lleida, Richard Cameron Rose, Devices and methods for speech recognition of vocabulary words with simultaneous detection and verification ,(1995)
Joel W. Parke, Gregory J. Gadbois, Even Stijn Van, James K. Baker, Charles E. Ingold, Pronunciation generation in speech recognition ASAJ. ,vol. 109, pp. 863- ,(1998)
Ove Andersen, Roland Kuhn, Ariane Lazarides, Paul Dalsgaard, Jürgen Haas, Elmar Noth, Comparison of two tree-structured approaches for grapheme-to-phoneme conversion international conference on spoken language processing. ,vol. 3, pp. 1700- 1703 ,(1996) , 10.1109/ICSLP.1996.607954
A. Lazarides, Y. Normandin, R. Kuhn, Improving decision trees for acoustic modeling international conference on spoken language processing. ,vol. 2, pp. 1053- 1056 ,(1996) , 10.1109/ICSLP.1996.607786
O. Nakamura, M. Yukishita, A high-speed morpheme-extraction system using dictionary database Proceedings. Fourth International Conference on Data Engineering. pp. 488- 495 ,(1988) , 10.1109/ICDE.1988.105495
A. Asadi, R. Schwartz, J. Makhoul, Automatic modeling for adding new words to a large-vocabulary continuous speech recognition system international conference on acoustics, speech, and signal processing. pp. 305- 308 ,(1991) , 10.1109/ICASSP.1991.150337