Markus Schnell, Michael Küstner, O. Jokisch, R. Hoffmann
{"title":"用于低资源系统的文本到语音","authors":"Markus Schnell, Michael Küstner, O. Jokisch, R. Hoffmann","doi":"10.1109/MMSP.2002.1203295","DOIUrl":null,"url":null,"abstract":"This article describes the restrictions and requirements low-resource systems to impose on text-to-speech (TTS) software. The most important point is available memory size, but computing time and implementation issues are discussed as well. For each restriction, one or more solutions are presented. The proferred solutions have been implemented by Infineon Technologies AG and the Technical University of Dresden.","PeriodicalId":398813,"journal":{"name":"2002 IEEE Workshop on Multimedia Signal Processing.","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2002-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":"{\"title\":\"Text-to-speech for low-resource systems\",\"authors\":\"Markus Schnell, Michael Küstner, O. Jokisch, R. Hoffmann\",\"doi\":\"10.1109/MMSP.2002.1203295\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This article describes the restrictions and requirements low-resource systems to impose on text-to-speech (TTS) software. The most important point is available memory size, but computing time and implementation issues are discussed as well. For each restriction, one or more solutions are presented. The proferred solutions have been implemented by Infineon Technologies AG and the Technical University of Dresden.\",\"PeriodicalId\":398813,\"journal\":{\"name\":\"2002 IEEE Workshop on Multimedia Signal Processing.\",\"volume\":\"10 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2002-12-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"9\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2002 IEEE Workshop on Multimedia Signal Processing.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/MMSP.2002.1203295\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2002 IEEE Workshop on Multimedia Signal Processing.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MMSP.2002.1203295","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
This article describes the restrictions and requirements low-resource systems to impose on text-to-speech (TTS) software. The most important point is available memory size, but computing time and implementation issues are discussed as well. For each restriction, one or more solutions are presented. The proferred solutions have been implemented by Infineon Technologies AG and the Technical University of Dresden.