口语技术的机器学习

Annals Series on History and Archaeology Academy of Romanian Scientists Pub Date : 2021-01-01 DOI:10.56082/annalsarsciinfo.2021.1-2.25

D. Burileanu, Serban Mihalache, Valentin Andrei, Alexandru-Lucian Georgescu, H. Cucu, C. Burileanu

{"title":"口语技术的机器学习","authors":"D. Burileanu, Serban Mihalache, Valentin Andrei, Alexandru-Lucian Georgescu, H. Cucu, C. Burileanu","doi":"10.56082/annalsarsciinfo.2021.1-2.25","DOIUrl":null,"url":null,"abstract":"Spoken language technology is one of the domains in which, in our days, machine learning algorithms and especially neural networks are used. Some applications will pe presented in this paper: detecting overlapped speech on short time frames (till 25ms), emotion recognition from speech (including speech stress detection and deceptive speech detection) and the performances of the last large vocabulary continuous speech recognition systems for Romanian developed in the SpeeD Laboratory, from Research Institute “CAMPUS”, University POLITEHNICA of Bucharest","PeriodicalId":32445,"journal":{"name":"Annals Series on History and Archaeology Academy of Romanian Scientists","volume":"37 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"MACHINE LEARNING FOR SPOKEN LANGUAGE TECHNOLOGY\",\"authors\":\"D. Burileanu, Serban Mihalache, Valentin Andrei, Alexandru-Lucian Georgescu, H. Cucu, C. Burileanu\",\"doi\":\"10.56082/annalsarsciinfo.2021.1-2.25\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Spoken language technology is one of the domains in which, in our days, machine learning algorithms and especially neural networks are used. Some applications will pe presented in this paper: detecting overlapped speech on short time frames (till 25ms), emotion recognition from speech (including speech stress detection and deceptive speech detection) and the performances of the last large vocabulary continuous speech recognition systems for Romanian developed in the SpeeD Laboratory, from Research Institute “CAMPUS”, University POLITEHNICA of Bucharest\",\"PeriodicalId\":32445,\"journal\":{\"name\":\"Annals Series on History and Archaeology Academy of Romanian Scientists\",\"volume\":\"37 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Annals Series on History and Archaeology Academy of Romanian Scientists\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.56082/annalsarsciinfo.2021.1-2.25\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals Series on History and Archaeology Academy of Romanian Scientists","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.56082/annalsarsciinfo.2021.1-2.25","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

口语技术是当今使用机器学习算法，尤其是神经网络的领域之一。本文将介绍一些应用:在短时间框架内检测重叠语音(直到25ms)，从语音中识别情感(包括语音重音检测和欺骗性语音检测)，以及在布加勒斯特POLITEHNICA大学“CAMPUS”研究所SpeeD实验室开发的最后一个大词汇连续语音识别系统的性能

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

MACHINE LEARNING FOR SPOKEN LANGUAGE TECHNOLOGY

Spoken language technology is one of the domains in which, in our days, machine learning algorithms and especially neural networks are used. Some applications will pe presented in this paper: detecting overlapped speech on short time frames (till 25ms), emotion recognition from speech (including speech stress detection and deceptive speech detection) and the performances of the last large vocabulary continuous speech recognition systems for Romanian developed in the SpeeD Laboratory, from Research Institute “CAMPUS”, University POLITEHNICA of Bucharest

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Annals Series on History and Archaeology Academy of Romanian Scientists

自引率

0.00%

发文量

审稿时长

15 weeks