{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T17:08:58Z","timestamp":1778605738371,"version":"3.51.4"},"reference-count":34,"publisher":"Elsevier BV","issue":"3-4","license":[{"start":{"date-parts":[[2002,3,1]],"date-time":"2002-03-01T00:00:00Z","timestamp":1014940800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2002,3]]},"DOI":"10.1016\/s0167-6393(01)00006-1","type":"journal-article","created":{"date-parts":[[2002,7,25]],"date-time":"2002-07-25T14:05:56Z","timestamp":1027605956000},"page":"247-265","source":"Crossref","is-referenced-by-count":17,"title":["RNN-based prosodic modeling for mandarin speech and its application to speech-to-text conversion"],"prefix":"10.1016","volume":"36","author":[{"given":"Wern-Jun","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan-Fu","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sin-Horng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(01)00006-1_BIB1","series-title":"Proc. IEEE Intern. Conf. Acoust., Speech, Signal Process. (ICASSP)","first-page":"903","article-title":"A multi-phase approach for fast spotting of large vocabulary Chinese keywords from Mandarin speech using prosodic information","author":"Bai","year":"1997"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB2","series-title":"Proc. Int. Conf. On Spoken Language Process. (ICSLP), Vol. 3","first-page":"1720","article-title":"Syntactic-prosodic labeling of large spontaneous speech data-base","author":"Batliner","year":"1996"},{"issue":"3","key":"10.1016\/S0167-6393(01)00006-1_BIB3","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1109\/89.668815","article-title":"HMM-based stressed speech modeling with application to improved synthesis and recognition of isolated speech under stress","volume":"6","author":"Bou-Ghazale","year":"1998","journal-title":"IEEE Trans. on Speech and Audio Processing"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB4","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1016\/0167-6393(93)90033-H","article-title":"Automatic detection of prosodic boundaries in speech","volume":"13","author":"Campbell","year":"1993","journal-title":"Speech Communication"},{"issue":"3","key":"10.1016\/S0167-6393(01)00006-1_BIB5","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1109\/89.668817","article-title":"An RNN-based prosodic information synthesizer for Mandarin text-to-speech","volume":"6","author":"Chen","year":"1998","journal-title":"IEEE Trans. on Speech and Audio Process."},{"key":"10.1016\/S0167-6393(01)00006-1_BIB6","series-title":"A Synchronic Phonology of Mandarin Chinese","author":"Cheng","year":"1973"},{"issue":"3","key":"10.1016\/S0167-6393(01)00006-1_BIB7","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1109\/89.496214","article-title":"On jointly learning the parameters in a character-synchronous integrated speech and language model","volume":"4","author":"Chiang","year":"1996","journal-title":"IEEE Trans. Speech and Audio Proc."},{"key":"10.1016\/S0167-6393(01)00006-1_BIB8","unstructured":"Chinese Knowledge Information Processing Group. 1995. The contents and descriptions of Sinica Corpus, Technical Report no. 95-02, Academia Sinica"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB9","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"Elman","year":"1990","journal-title":"Cognitive Science"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB10","series-title":"Proc. Int. Conf. On Spoken Language Process. (ICSLP)","first-page":"1716","article-title":"Consistency in transcription and labeling of German intonation with GToBI","author":"Grice","year":"1996"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB11","series-title":"Neural Networks \u2013 A Comprehensive Foundation","author":"Haykin","year":"1994"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB12","series-title":"Proc. Eur. Conf. on Speech Commun. Technol. (EUROSPEECH), Vol. 1","first-page":"311","article-title":"A method of representing fundamental frequency contours of Japanese using statistical models of moraic transition","author":"Hirose","year":"1997"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB13","series-title":"Proc. IEEE Intern. Conf. Acoust., Speech, Signal Process. (ICASSP), Vol. 1","first-page":"25","article-title":"Accent type recognition and syntactic boundary detection of Japanese using statistical modeling of moraic transitions of fundamental frequency contours","author":"Hirose","year":"1998"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB14","series-title":"Proc. Int. Conf. On Spoken Language Process. (ICSLP), Vol. 1","first-page":"809","article-title":"Use of prosodic information to integrate acoustic and linguistic knowledge in continuous mandarin speech recognition with very large vocabulary","author":"Hsieh","year":"1996"},{"issue":"3","key":"10.1016\/S0167-6393(01)00006-1_BIB15","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1109\/89.294360","article-title":"An efficient algorithm for syllable hypothesization in continuous Mandarin speech recognition","volume":"2","author":"Huang","year":"1994","journal-title":"IEEE Trans on Speech and Audio Process"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB16","series-title":"Proc. IEEE Intern. Conf. Acoust., Speech, Signal Process. (ICASSP), Vol. II","first-page":"169","article-title":"A generalized model for utilizing prosodic information in continuous speech recognition","author":"Hunt","year":"1994"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB17","series-title":"Proc. Eur. Conf. On Speech Commun. Technol. (EUROSPEECH), Vol. 1","first-page":"231","article-title":"Prosodic word boundary detection using mora transition modeling of fundamental frequency contours speaker-independent experiments","author":"Iwano","year":"1999"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB18","series-title":"Proc. Int. Conf. On Spoken Language Process. (ICSLP), Vol. 3","first-page":"599","article-title":"Representing prosodic words using statistical models of moraic transition of fundamental frequency contours of Japanese","author":"Iwano","year":"1998"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB19","series-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Vol. 1","first-page":"133","article-title":"Prosodic word boundary detection using statistical modeling of moraic fundamental frequency contours and its use for continuous speech recognition","author":"Iwano","year":"1999"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB20","series-title":"Proc. Eur. Conf. On Speech Commun. Technol. (EUROSPEECH), Vol. 2","first-page":"1333","article-title":"Prosodic scoring of word hypotheses graphs","author":"Kompe","year":"1995"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB21","series-title":"Proc. IEEE Intern. Conf. Acoust., Speech, Signal Process. (ICASSP)","first-page":"811","article-title":"Improving parsing of spontaneous speech with the help of prosodic boundaries","author":"Kompe","year":"1997"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB22","series-title":"Proc. IEEE Intern. Conf. Acoust., Speech, Signal Process. (ICASSP)","first-page":"57","article-title":"Golden Mandarin (III) a user-adaptive prosodic-segment-based mandarin dictation machine for Chinese language with very large vocabulary","author":"Lyu","year":"1995"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB23","series-title":"Linear Prediction of Speech","author":"Markel","year":"1976"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB24","series-title":"Neural Networks and Speech Processing","author":"Morgan","year":"1991"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB25","series-title":"Proc. IEEE Intern. Conf. Acoust., Speech, Signal Process (ICASSP)","first-page":"75","article-title":"Prosodic processing and its use in verbmobil","author":"Niemann","year":"1997"},{"issue":"6","key":"10.1016\/S0167-6393(01)00006-1_BIB26","doi-asserted-by":"crossref","first-page":"2956","DOI":"10.1121\/1.401770","article-title":"The Use of prosody in syntactic disambiguation","volume":"90","author":"Price","year":"1991","journal-title":"J. Acoust. Soc. Am."},{"issue":"2","key":"10.1016\/S0167-6393(01)00006-1_BIB27","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1109\/72.279192","article-title":"An application of recurrent nets to phone probability estimation","volume":"5","author":"Robinson","year":"1994","journal-title":"IEEE Trans. on Neural Networks"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB28","series-title":"Proc. Int. Conf. On Spoken Language Processing (ICSLP), Vol. 2","first-page":"867","article-title":"TOBI: a standard for labeling English prosody","author":"Silverman","year":"1992"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB29","unstructured":"Su, Y.S., 1994. A study on automatic segmentation and tagging of Chinese sentence. Master Thesis, National Chiao Tung University, Taiwan, ROC"},{"issue":"5","key":"10.1016\/S0167-6393(01)00006-1_BIB30","doi-asserted-by":"crossref","first-page":"2637","DOI":"10.1121\/1.411274","article-title":"Tone recognition of continuous mandarin speech assisted with prosodic information","volume":"96","author":"Wang","year":"1994","journal-title":"J. Acoust. Soc. Am."},{"issue":"4","key":"10.1016\/S0167-6393(01)00006-1_BIB31","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1109\/89.326607","article-title":"Automatic labeling of prosodic patterns","volume":"2","author":"Wightman","year":"1994","journal-title":"IEEE Trans. Speech and Audio Proc."},{"key":"10.1016\/S0167-6393(01)00006-1_BIB32","series-title":"Proc. Conf. on Phonetics of the Languages in China","first-page":"125","article-title":"The formalization of segmental coarticulatory variants in Chinese synthesis system","author":"Wu","year":"1998"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB33","series-title":"Proc. Int. Conf. On Spoken Language Process. (ICSLP), Vol. 3","first-page":"1371","article-title":"An intelligent and efficient word-class-based Chinese language model for Mandarin speech recognition with very large vocabulary","author":"Yang","year":"1994"},{"key":"10.1016\/S0167-6393(01)00006-1_BIB34","unstructured":"Yin, Y.M., 1989. Phonological Aspects of Word Formation in Mandarin Chinese. University Microfilms International"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639301000061?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639301000061?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,4,28]],"date-time":"2019-04-28T18:20:27Z","timestamp":1556475627000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639301000061"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002,3]]},"references-count":34,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2002,3]]}},"alternative-id":["S0167639301000061"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(01)00006-1","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2002,3]]}}}