{"title":"A neural network speech recognizer based on the both acoustic steady portions and transitions","authors":"Seyyed Ali Seyyed Salehi","doi":"10.21437/icslp.2000-408","DOIUrl":"https://doi.org/10.21437/icslp.2000-408","url":null,"abstract":"","PeriodicalId":420904,"journal":{"name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115790232","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":"Evidence for demodulation in speech perception","authors":"H. Traunmüller","doi":"10.21437/icslp.2000-653","DOIUrl":"https://doi.org/10.21437/icslp.2000-653","url":null,"abstract":"According to the Modulation Theory, speakers modulate their voice with linguistic gestures, and listeners demodulate the signal in order to separate the linguistic from the expressive and organic i ...","PeriodicalId":420904,"journal":{"name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","volume":"158 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116111493","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":"Linguistic-prosodic processing for text-to-speech synthesis in italian","authors":"Philippe Boula de Mareüil","doi":"10.21437/icslp.2000-173","DOIUrl":"https://doi.org/10.21437/icslp.2000-173","url":null,"abstract":"","PeriodicalId":420904,"journal":{"name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131376181","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":"Application of speaker authentication technology to a telephone dialogue system","authors":"Leandro Rodríguez Liñares, Carmen García Mateo","doi":"10.21437/icslp.2000-250","DOIUrl":"https://doi.org/10.21437/icslp.2000-250","url":null,"abstract":"TelCorreo is a dialogue system that allows users to manage their e-mail accounts using the telephone. Regarding speech technology, TelCorreo is a highly demanding application, since it needs of state-of-art text-to-speech system, speech recognizer and speaker authentifier. The main features of TelCorreo are described in [1] and [2]. In this paper, we will concentrate on the speaker authentication module. Presently, there are very few speaker recognition systems working in real-world applications. The reason is that the performance achieved by most of the techniques proposed in the literature dramatically drops for out-of-lab conditions. Real-world conditions raise new issues to be considered and a compromise between performance and feasibility must be achieved. We studied the problem of how to increase the performance of a speaker authentifier system by combining the outputs of an utterance verifier and a speaker verifier (the former recognizes the actual verbal content of the speech, while the latter uses speaker voice by itself as a way of verifying the identity). We have developed a speaker authentifier module suitable to be integrated in a real-world dialogue system. In this paper, we describe the main relevant aspects of this module. The rest of this paper is structured as follows. Section 1 introduces TelCorreo and its speaker authentication module. Section 2 explains the module design from the users' point of view, while section 3 presents TelCorreoDB: an experimental frame adequate for testing the speaker authentication technology used in TelCorreo. Section 4 presents the implementation details. Finally, some conclusions","PeriodicalId":420904,"journal":{"name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130092780","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}