{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T00:10:22Z","timestamp":1683245422321},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[1997,12,1]],"date-time":"1997-12-01T00:00:00Z","timestamp":880934400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[1997,12]]},"DOI":"10.1007\/bf02208826","type":"journal-article","created":{"date-parts":[[2005,10,5]],"date-time":"2005-10-05T21:31:31Z","timestamp":1128547891000},"page":"145-153","source":"Crossref","is-referenced-by-count":2,"title":["Speech recognition and synthesis technology development at NTT for telecommunications services"],"prefix":"10.1007","volume":"2","author":[{"given":"Kazuo","family":"Hakoda","sequence":"first","affiliation":[]},{"given":"Mikio","family":"Kitai","sequence":"additional","affiliation":[]},{"given":"Shigeki","family":"Sagayama","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"BF02208826_CR1","unstructured":"Abe, M., Hakoda, K., and Tsukada, H. (1996). An information retrieval system from text database using text-to-speech.Proc. AVIOS'96, pp. 189\u2013196."},{"key":"BF02208826_CR2","doi-asserted-by":"crossref","unstructured":"Charpentier, F. and Moulines, E. (1989). Pitch synchronous waveform processing techniques for text-to-speech synthesis using diphones.Proc. Eurospeech'89, pp. 13\u201319.","DOI":"10.21437\/Eurospeech.1989-172"},{"key":"BF02208826_CR3","unstructured":"Darrel, S. and Bernie, R. (1994). DECtalk software in a desktop environment.Proc. AVIOS'94, pp. 189\u2013193."},{"key":"BF02208826_CR4","unstructured":"Hakoda, K., Nakajima, S., Hirokawa, T., and Mizuno, H. (1990). A new Japanese text-to-speech synthesizer based on COC synthesized method.Proc. ICSLP'90, pp. 809\u2013812."},{"key":"BF02208826_CR5","unstructured":"Hakoda, K., Hirokawa, T., Tsukada, H., Yoshida, Y., and Mizuno, H. (1995). Japanese text-to-speech software based on waveform concatenation method.Proc. AVIOS'95, pp. 65\u201372."},{"issue":"11","key":"BF02208826_CR6","first-page":"1964","volume":"E76-A","author":"T. Hirokawa","year":"1993","unstructured":"Hirokawa, T., Itoh, K., and Sato, H. (1993). High quality speech synthesis system based on waveform concatenation of phoneme segment.IEICE Trans. Fundamentals, E76-A(11): 1964\u20131970.","journal-title":"IEICE Trans. Fundamentals"},{"issue":"2","key":"BF02208826_CR7","first-page":"145","volume":"35","author":"S. Ikehara","year":"1986","unstructured":"Ikehara, S., Murakami, K., Miyazaki, M., and Ohyama, Y. (1986). Construction of Japanese text-to-speech system.ECL Tech. J., 35(2): 145\u2013155 (in Japanese).","journal-title":"ECL Tech. J."},{"key":"BF02208826_CR8","unstructured":"Imamura, A. and Suzuki, Y. (1990). Speaker-independent word spotting and a tranputer-based implementation.Proc. ICSLP'90, pp. 537\u2013540."},{"key":"BF02208826_CR9","unstructured":"Intoh, K. and Miki, S. (1988). Speaker independent isolated word recognition board and its application.American Voice I\/O Systems Applications Conf., AVIOS'88."},{"key":"BF02208826_CR10","unstructured":"Itakura, F. (1975). Line spectrum representation of linear prediction coefficients of speech signal.Trans. of the Committee on Speech Research, ASJ, S75-34."},{"key":"BF02208826_CR11","unstructured":"Itakura, F. and Saito, S. (1969). Speech analysis-synthesis system based on the partial autocorrelation coefficient.Acoust. Soc. of Japan Meeting, pp. 199\u2013200 (in Japanese)."},{"key":"BF02208826_CR12","unstructured":"Minami, Y, Shikano, K., Yamada, T., and Matsuoka, T. (1992). Very-large-vocabulary continuous speech recognition system for telephone directory assistance.Proc. IVTTA'92."},{"key":"BF02208826_CR13","first-page":"327","volume":"3-5-6","author":"K. Momosaki","year":"1994","unstructured":"Momosaki, K., Hara, Y., Shiga, Y., Kaseno, O., Tamanaka, N., Nitta, T., and Kobayashi, K. (1994). A Japanese TTS software for personal computers.ASJ'94 Autumn Meeting.3-5-6, pp. 327\u2013328 (in Japanese).","journal-title":"ASJ'94 Autumn Meeting"},{"key":"BF02208826_CR14","unstructured":"Nakatsu, R. and Ishii, N. (1987). Voice response and recognition system for telephone information services.Proc. of SPEECH TECH'87, pp. 168\u2013172."},{"key":"BF02208826_CR15","doi-asserted-by":"crossref","unstructured":"Noda, Y and Sagayama, S. (1995). Fast and accurate beam search using forward heuristic functions in HMM-LR speech recognition.Proc. Eurospeech'95 (Madrid), WEamIA.5, pp. 913\u2013916.","DOI":"10.21437\/Eurospeech.1995-205"},{"key":"BF02208826_CR16","unstructured":"Sato, H., Sagisaka, Y, Kogure, K., and Sagayama, S. (1982). Investigation on Japanese text-to-speech conversion.Trans. of the Committee on Speech Research, S82-08 (in Japanese)."},{"key":"BF02208826_CR17","doi-asserted-by":"crossref","unstructured":"Takahashi, J. and Sagayama, S. (1994). Fast telephone channel adaptation based on vector field smoothing technique.Proc. IVTTA'94 Workshop, pp. 97\u2013100.","DOI":"10.1109\/IVTTA.1994.341536"},{"key":"BF02208826_CR18","doi-asserted-by":"crossref","unstructured":"Takahashi, J. and Sagayama, S. (1995). Vector-field-smoothed bayesian learning for incremental speaker adaptation.Proc. ICASSP95 (Detroit), pp. 696\u2013699.","DOI":"10.1109\/ICASSP.1995.479789"},{"key":"BF02208826_CR19","doi-asserted-by":"crossref","unstructured":"Takahashi, K., Iwata, K., Mitome, Y, and Nagano, K. (1994). Japanese text-to-speech conversion software for personal computers.Proc. ICSLPV4, pp. 1743\u20131746.","DOI":"10.21437\/ICSLP.1994-191"},{"key":"BF02208826_CR20","doi-asserted-by":"crossref","unstructured":"Takahashi, S. and Sagayama, S. (1995). Four-level tied structure for efficient representation of acoustic modeling.Proc. ICASSP'95 (Detroit), pp. 520\u2013523.","DOI":"10.1109\/ICASSP.1995.479643"},{"key":"BF02208826_CR21","doi-asserted-by":"crossref","unstructured":"Tomita, M. (1991).Generalized LR Parsing. Kluwer Academic Publishers.","DOI":"10.1007\/978-1-4615-4034-2"},{"key":"BF02208826_CR22","first-page":"123","volume":"3-8-8","author":"T. Yamada","year":"1994","unstructured":"Yamada, T. and Sagayama, S. (1994). An implementation of LR parser using context-dependent phone models.Proc. JASJ Conf., 3-8-8, pp. 123\u2013124 (in Japanese).","journal-title":"Proc. JASJ Conf."},{"key":"BF02208826_CR23","doi-asserted-by":"crossref","unstructured":"Yoshida, Y, Nakajima, S., Hakoda, K., and Hirokawa, T. (1996). A new method of generating speech synthesis units based on phonological knowledge and clustering technique.Proc. ICSLP'96, pp. 1712\u20131715.","DOI":"10.1109\/ICSLP.1996.607957"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/BF02208826.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/BF02208826\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/BF02208826","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,4]],"date-time":"2023-05-04T23:44:02Z","timestamp":1683243842000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/BF02208826"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1997,12]]},"references-count":23,"journal-issue":{"issue":"2","published-print":{"date-parts":[[1997,12]]}},"alternative-id":["BF02208826"],"URL":"https:\/\/doi.org\/10.1007\/bf02208826","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[1997,12]]}}}