通过模拟人类听觉感知的某些特性，实现了一种高效的独立于说话人的自动语音识别

ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing Pub Date : 1987-04-06 DOI:10.1109/ICASSP.1987.1169803

H. Hermansky

{"title":"通过模拟人类听觉感知的某些特性，实现了一种高效的独立于说话人的自动语音识别","authors":"H. Hermansky","doi":"10.1109/ICASSP.1987.1169803","DOIUrl":null,"url":null,"abstract":"An auditory model of speech perception, the Perceptually based linear predictive analysis with Root power sum metric (PLP-RPS), is applied as the front-end of an automatic speech recognizer (ASR). The PLP-RPS front-end is compared with standard linear predictive-cepstral metric (LP-CEP) front-end, and with LP-RPS and PLP-CEP front-ends. The two-spectral-peak models are the most efficient in modeling of linguistic information in speech. Consequently, in speaker-independent ASR, high analysis order front-ends are less effective than low-order front-ends. Synthetic speech is used for front-end evaluation. Some of perceptual inconsistencies of standard LP front-ends are alleviated in PLP front-ends. The PLP-RPS front-end is most sensitive to harmonic structure of speech spectrum. Perceptual experiments indicate similar tendencies in human auditory perception.","PeriodicalId":140810,"journal":{"name":"ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing","volume":"3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1987-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"34","resultStr":"{\"title\":\"An efficient speaker-independent automatic speech recognition by simulation of some properties of human auditory perception\",\"authors\":\"H. Hermansky\",\"doi\":\"10.1109/ICASSP.1987.1169803\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"An auditory model of speech perception, the Perceptually based linear predictive analysis with Root power sum metric (PLP-RPS), is applied as the front-end of an automatic speech recognizer (ASR). The PLP-RPS front-end is compared with standard linear predictive-cepstral metric (LP-CEP) front-end, and with LP-RPS and PLP-CEP front-ends. The two-spectral-peak models are the most efficient in modeling of linguistic information in speech. Consequently, in speaker-independent ASR, high analysis order front-ends are less effective than low-order front-ends. Synthetic speech is used for front-end evaluation. Some of perceptual inconsistencies of standard LP front-ends are alleviated in PLP front-ends. The PLP-RPS front-end is most sensitive to harmonic structure of speech spectrum. Perceptual experiments indicate similar tendencies in human auditory perception.\",\"PeriodicalId\":140810,\"journal\":{\"name\":\"ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing\",\"volume\":\"3 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1987-04-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"34\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICASSP.1987.1169803\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASSP.1987.1169803","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 34

摘要

将基于感知的线性预测分析与根幂和度量(PLP-RPS)作为语音自动识别器(ASR)的前端。将PLP-RPS前端与标准线性预测-倒谱度量(LP-CEP)前端、LP-RPS和PLP-CEP前端进行比较。双谱峰模型是最有效的语言信息建模方法。因此，在与说话人无关的ASR中，高分析阶数前端的效率低于低阶阶数前端。前端评价采用合成语音。标准LP前端的一些感知不一致性在PLP前端得到了缓解。PLP-RPS前端对语音频谱的谐波结构最为敏感。知觉实验表明，人类听觉也有类似的倾向。

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

An efficient speaker-independent automatic speech recognition by simulation of some properties of human auditory perception

An auditory model of speech perception, the Perceptually based linear predictive analysis with Root power sum metric (PLP-RPS), is applied as the front-end of an automatic speech recognizer (ASR). The PLP-RPS front-end is compared with standard linear predictive-cepstral metric (LP-CEP) front-end, and with LP-RPS and PLP-CEP front-ends. The two-spectral-peak models are the most efficient in modeling of linguistic information in speech. Consequently, in speaker-independent ASR, high analysis order front-ends are less effective than low-order front-ends. Synthetic speech is used for front-end evaluation. Some of perceptual inconsistencies of standard LP front-ends are alleviated in PLP front-ends. The PLP-RPS front-end is most sensitive to harmonic structure of speech spectrum. Perceptual experiments indicate similar tendencies in human auditory perception.

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

ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing

自引率

0.00%

发文量