X. Menéndez-Pidal, J. Ferreiros, R. Córdoba, J. Pardo
{"title":"Recent work in hybrid neural networks and HMM systems in CSR tasks","authors":"X. Menéndez-Pidal, J. Ferreiros, R. Córdoba, J. Pardo","doi":"10.21437/ICSLP.1994-393","DOIUrl":"https://doi.org/10.21437/ICSLP.1994-393","url":null,"abstract":"","PeriodicalId":90685,"journal":{"name":"Proceedings : ICSLP. International Conference on Spoken Language Processing","volume":"70 1","pages":"1515-1518"},"PeriodicalIF":0.0,"publicationDate":"1994-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90830748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Phonetic underspecification in schwa","authors":"Yuko Kondo","doi":"10.21437/ICSLP.1994-81","DOIUrl":"https://doi.org/10.21437/ICSLP.1994-81","url":null,"abstract":"","PeriodicalId":90685,"journal":{"name":"Proceedings : ICSLP. International Conference on Spoken Language Processing","volume":"44 1","pages":"311-314"},"PeriodicalIF":0.0,"publicationDate":"1994-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91279437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Inferring linguistic structure in spoken language","authors":"M. Woszczyna, A. Waibel","doi":"10.21437/ICSLP.1994-226","DOIUrl":"https://doi.org/10.21437/ICSLP.1994-226","url":null,"abstract":"We demonstrate the applications of Markov Chains and HMMs to modeling of the underlying structure in spontaneous spoken language. Experiments with supervised training cover the detection of the current dialog state and identi cation of the speech act as used by the speech translation component in our JANUS Speech-to-Speech Translation System. HMM training with hidden states is used to uncover other levels of structure in the task. The possible use of the model for perplexity reduction in a continuous speech recognition system is also demonstrated. To achieve improvement over a state independent bigram language model, great care must be taken to keep the number of model parameters small in the face of limited amounts of training data from transcribed spontaneous speech.","PeriodicalId":90685,"journal":{"name":"Proceedings : ICSLP. International Conference on Spoken Language Processing","volume":"15 1","pages":"847-850"},"PeriodicalIF":0.0,"publicationDate":"1994-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89641814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Discourse structure for spontaneous spoken interactions: multi-speaker vs. human-computer dialogs","authors":"S. Young","doi":"10.21437/ICSLP.1994-559","DOIUrl":"https://doi.org/10.21437/ICSLP.1994-559","url":null,"abstract":"","PeriodicalId":90685,"journal":{"name":"Proceedings : ICSLP. International Conference on Spoken Language Processing","volume":"1 1","pages":"2227-2230"},"PeriodicalIF":0.0,"publicationDate":"1994-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89693970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Relationship between acoustic measures of vocal perturbation and perceptual judgments of breathiness, harshness, and hoarseness","authors":"F. Minifie, D. Huang, Jordan R. Green","doi":"10.21437/ICSLP.1994-502","DOIUrl":"https://doi.org/10.21437/ICSLP.1994-502","url":null,"abstract":"","PeriodicalId":90685,"journal":{"name":"Proceedings : ICSLP. International Conference on Spoken Language Processing","volume":"18 1","pages":"1999-2002"},"PeriodicalIF":0.0,"publicationDate":"1994-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89349546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Acceptability of temporal modification in consonant and vowel onsets","authors":"H. Kato, M. Tsuzaki, Y. Sagisaka","doi":"10.21437/ICSLP.1994-497","DOIUrl":"https://doi.org/10.21437/ICSLP.1994-497","url":null,"abstract":"","PeriodicalId":90685,"journal":{"name":"Proceedings : ICSLP. International Conference on Spoken Language Processing","volume":"283 1","pages":"1979-1983"},"PeriodicalIF":0.0,"publicationDate":"1994-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76830373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Temporal organization of bimodal speech information","authors":"P. Smeele, A. Sittig, V. J. Heuven","doi":"10.21437/ICSLP.1994-372","DOIUrl":"https://doi.org/10.21437/ICSLP.1994-372","url":null,"abstract":"","PeriodicalId":90685,"journal":{"name":"Proceedings : ICSLP. International Conference on Spoken Language Processing","volume":"18 1","pages":"1431-1434"},"PeriodicalIF":0.0,"publicationDate":"1994-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78074947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Dynamic probabilistic grammar for spoken language disambiguation","authors":"T. Kawabata","doi":"10.21437/ICSLP.1994-211","DOIUrl":"https://doi.org/10.21437/ICSLP.1994-211","url":null,"abstract":"","PeriodicalId":90685,"journal":{"name":"Proceedings : ICSLP. International Conference on Spoken Language Processing","volume":"45 1","pages":"787-790"},"PeriodicalIF":0.0,"publicationDate":"1994-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74945203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An algorithm to reconstruct wideband speech from narrowband speech based on codebook mapping","authors":"Y. Yoshida, M. Abe","doi":"10.21437/ICSLP.1994-412","DOIUrl":"https://doi.org/10.21437/ICSLP.1994-412","url":null,"abstract":"","PeriodicalId":90685,"journal":{"name":"Proceedings : ICSLP. International Conference on Spoken Language Processing","volume":"90 1","pages":"1591-1594"},"PeriodicalIF":0.0,"publicationDate":"1994-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74742860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
E. Vatikiotis-Bateson, M. Tiede, Y. Wada, V. Gracco, M. Kawato
{"title":"Phoneme extraction using via point estimation of real speech","authors":"E. Vatikiotis-Bateson, M. Tiede, Y. Wada, V. Gracco, M. Kawato","doi":"10.21437/ICSLP.1994-160","DOIUrl":"https://doi.org/10.21437/ICSLP.1994-160","url":null,"abstract":"","PeriodicalId":90685,"journal":{"name":"Proceedings : ICSLP. International Conference on Spoken Language Processing","volume":"195 1","pages":"631-634"},"PeriodicalIF":0.0,"publicationDate":"1994-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72943275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}