实现的MFCC和基于hmm的语音识别系统性能分析

2020 IEEE 2nd International Conference on Artificial Intelligence in Engineering and Technology (IICAIET) Pub Date : 2020-09-26 DOI:10.1109/IICAIET49801.2020.9257823

Marlyn Maseri, Mazlina Mamat

{"title":"实现的MFCC和基于hmm的语音识别系统性能分析","authors":"Marlyn Maseri, Mazlina Mamat","doi":"10.1109/IICAIET49801.2020.9257823","DOIUrl":null,"url":null,"abstract":"This paper describes the performance analysis of designed speech recognition system whereby the front end method uses MFCCs feature extraction algorithm and defined HMM recognition as the back end. The dataset includes 30 phonemes and 2200 utterances by different speakers. Each speech signal is sampled to 16kHz, 16-bit PCM, and in a mono channel format. The extracted feature of each signal consists of 39 feature vectors which are 12 Mel Cepstrum Coefficients, Log Energy, Delta (first-order derivative) coefficients, and Acceleration coefficients (second-order derivative). The Baum-Welch algorithm is applied for HMM training and the Viterbi algorithms for decoding. The overall system performance accuracy of this experiment is 95.00%.","PeriodicalId":300885,"journal":{"name":"2020 IEEE 2nd International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Performance Analysis of Implemented MFCC and HMM-based Speech Recognition System\",\"authors\":\"Marlyn Maseri, Mazlina Mamat\",\"doi\":\"10.1109/IICAIET49801.2020.9257823\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper describes the performance analysis of designed speech recognition system whereby the front end method uses MFCCs feature extraction algorithm and defined HMM recognition as the back end. The dataset includes 30 phonemes and 2200 utterances by different speakers. Each speech signal is sampled to 16kHz, 16-bit PCM, and in a mono channel format. The extracted feature of each signal consists of 39 feature vectors which are 12 Mel Cepstrum Coefficients, Log Energy, Delta (first-order derivative) coefficients, and Acceleration coefficients (second-order derivative). The Baum-Welch algorithm is applied for HMM training and the Viterbi algorithms for decoding. The overall system performance accuracy of this experiment is 95.00%.\",\"PeriodicalId\":300885,\"journal\":{\"name\":\"2020 IEEE 2nd International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)\",\"volume\":\"2 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-09-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE 2nd International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IICAIET49801.2020.9257823\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE 2nd International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IICAIET49801.2020.9257823","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

本文描述了所设计的语音识别系统的性能分析，其中前端方法使用MFCCs特征提取算法，后端定义HMM识别。该数据集包括30个音素和2200个不同说话者的话语。每个语音信号被采样到16kHz, 16位PCM，并在单声道格式。每个信号提取的特征由39个特征向量组成，这些特征向量分别是12个Mel倒谱系数、Log Energy系数、Delta(一阶导数)系数和加速度系数(二阶导数)。HMM训练采用Baum-Welch算法，解码采用Viterbi算法。本实验的整体系统性能精度为95.00%。

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

Performance Analysis of Implemented MFCC and HMM-based Speech Recognition System

This paper describes the performance analysis of designed speech recognition system whereby the front end method uses MFCCs feature extraction algorithm and defined HMM recognition as the back end. The dataset includes 30 phonemes and 2200 utterances by different speakers. Each speech signal is sampled to 16kHz, 16-bit PCM, and in a mono channel format. The extracted feature of each signal consists of 39 feature vectors which are 12 Mel Cepstrum Coefficients, Log Energy, Delta (first-order derivative) coefficients, and Acceleration coefficients (second-order derivative). The Baum-Welch algorithm is applied for HMM training and the Viterbi algorithms for decoding. The overall system performance accuracy of this experiment is 95.00%.

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

2020 IEEE 2nd International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)

自引率

0.00%

发文量