从不准确的构音特征中进行独立于说话人的元音分类

Proceedings of the 1992 South African Symposium on Communications and Signal Processing Pub Date : 1992-09-11 DOI:10.1109/COMSIG.1992.274313

J. Scalkwyk, P. Vermeulen, E. Barnard

{"title":"从不准确的构音特征中进行独立于说话人的元音分类","authors":"J. Scalkwyk, P. Vermeulen, E. Barnard","doi":"10.1109/COMSIG.1992.274313","DOIUrl":null,"url":null,"abstract":"Formant extraction is a notoriously unreliable procedure. Neural networks on the other hand are able to deal with such inaccurate data. It is shown that a multilayer perceptron is able to classify five types of vowels with acceptable accuracy (approximately 74%) when operating on very simple formant-based features.<<ETX>>","PeriodicalId":342857,"journal":{"name":"Proceedings of the 1992 South African Symposium on Communications and Signal Processing","volume":"5 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1992-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Speaker-independent vowel classification from inaccurate formant features\",\"authors\":\"J. Scalkwyk, P. Vermeulen, E. Barnard\",\"doi\":\"10.1109/COMSIG.1992.274313\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Formant extraction is a notoriously unreliable procedure. Neural networks on the other hand are able to deal with such inaccurate data. It is shown that a multilayer perceptron is able to classify five types of vowels with acceptable accuracy (approximately 74%) when operating on very simple formant-based features.<<ETX>>\",\"PeriodicalId\":342857,\"journal\":{\"name\":\"Proceedings of the 1992 South African Symposium on Communications and Signal Processing\",\"volume\":\"5 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1992-09-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 1992 South African Symposium on Communications and Signal Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/COMSIG.1992.274313\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 1992 South African Symposium on Communications and Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/COMSIG.1992.274313","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

峰提取是出了名的不可靠的程序。另一方面，神经网络能够处理这种不准确的数据。结果表明，当对非常简单的基于共振峰的特征进行操作时，多层感知器能够以可接受的准确率(约74%)对五种类型的元音进行分类

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

Speaker-independent vowel classification from inaccurate formant features

Formant extraction is a notoriously unreliable procedure. Neural networks on the other hand are able to deal with such inaccurate data. It is shown that a multilayer perceptron is able to classify five types of vowels with acceptable accuracy (approximately 74%) when operating on very simple formant-based features.<>

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

Proceedings of the 1992 South African Symposium on Communications and Signal Processing

自引率

0.00%

发文量