Title :
Speech recognition for Japanese spoken language
Author_Institution :
NTT Human Interface Labs., Musashino, Japan
Abstract :
This paper overviews the speech recognition issues for the Japanese language, and introduces three research projects conducted at NTT (Nippon Telegraph and Telephone) Human Interface Laboratories and ATR Interpreting Telephony Research Laboratories. The first topic is stochastic language models for the sequences of Japanese characters to be used in a Japanese dictation system with unlimited vocabulary. The second topic is an accurate and efficient algorithm for very-large-vocabulary continuous speech recognition based on an HMM-LR algorithm. This algorithm was applied to a telephone directory assistance system that recognizes spontaneous speech having a vocabulary size of roughly 80000. The third topic is a continuous speech recognition system based on strategies of the phoneme-context-dependent (allophonic) modeling and parsing
Keywords :
dictation; hidden Markov models; natural languages; speech recognition; speech recognition equipment; stochastic processes; telephone systems; ATR Interpreting Telephony Research Laboratories; HMM-LR algorithm; Japanese characters; Japanese dictation system; Japanese spoken language; NTT; Nippon Telegraph and Telephone; allophonic modeling; continuous speech recognition; continuous speech recognition system; parsing; phoneme-context-dependent modeling; research project; speech recognition; spontaneous speech recognition; stochastic language models; telephone directory assistance system; vocabulary; Character recognition; Context modeling; Databases; Electrical capacitance tomography; Humans; Laboratories; Natural languages; Speech recognition; Testing; Vocabulary;
Conference_Titel :
Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on
Print_ISBN :
0-7803-1865-X
DOI :
10.1109/SIPNN.1994.344950
