基于Odia的自动语音识别系统

2015 International Conference on Microwave, Optical and Communication Engineering (ICMOCE) Pub Date : 2015-12-01 DOI:10.1109/ICMOCE.2015.7489765

Biswajit Karan, Jayaprakash Sahoo, P. K. Sahu

{"title":"基于Odia的自动语音识别系统","authors":"Biswajit Karan, Jayaprakash Sahoo, P. K. Sahu","doi":"10.1109/ICMOCE.2015.7489765","DOIUrl":null,"url":null,"abstract":"In this paper, we presents a scheme of implementation of automatic speech recognition system using Odia language. The proposed system is realized using Kaldi toolkit for automatic recognition of district models of the state of Odisha. We investigate the monophone and triphone model for Odia speech recognition. Acoustic modeling of Odia speech recognition was performed using HMM and GMM. A significant reduction in word error rate (WER) was observed using the triphone model. We report the preliminary speech recognition results using Kaldi speech toolkit.","PeriodicalId":352568,"journal":{"name":"2015 International Conference on Microwave, Optical and Communication Engineering (ICMOCE)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":"{\"title\":\"Automatic speech recognition based Odia system\",\"authors\":\"Biswajit Karan, Jayaprakash Sahoo, P. K. Sahu\",\"doi\":\"10.1109/ICMOCE.2015.7489765\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we presents a scheme of implementation of automatic speech recognition system using Odia language. The proposed system is realized using Kaldi toolkit for automatic recognition of district models of the state of Odisha. We investigate the monophone and triphone model for Odia speech recognition. Acoustic modeling of Odia speech recognition was performed using HMM and GMM. A significant reduction in word error rate (WER) was observed using the triphone model. We report the preliminary speech recognition results using Kaldi speech toolkit.\",\"PeriodicalId\":352568,\"journal\":{\"name\":\"2015 International Conference on Microwave, Optical and Communication Engineering (ICMOCE)\",\"volume\":\"45 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"12\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 International Conference on Microwave, Optical and Communication Engineering (ICMOCE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICMOCE.2015.7489765\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 International Conference on Microwave, Optical and Communication Engineering (ICMOCE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICMOCE.2015.7489765","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 12

摘要

本文提出了一种基于Odia语言的语音自动识别系统的实现方案。该系统利用Kaldi工具实现了对奥里萨邦地区模型的自动识别。我们研究了用于Odia语音识别的单声道和三声道模型。利用HMM和GMM对Odia语音识别进行声学建模。使用三音器模型可以显著降低单词错误率(WER)。我们报告了使用Kaldi语音工具包的初步语音识别结果。

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

Automatic speech recognition based Odia system

In this paper, we presents a scheme of implementation of automatic speech recognition system using Odia language. The proposed system is realized using Kaldi toolkit for automatic recognition of district models of the state of Odisha. We investigate the monophone and triphone model for Odia speech recognition. Acoustic modeling of Odia speech recognition was performed using HMM and GMM. A significant reduction in word error rate (WER) was observed using the triphone model. We report the preliminary speech recognition results using Kaldi speech toolkit.

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

2015 International Conference on Microwave, Optical and Communication Engineering (ICMOCE)

自引率

0.00%

发文量