UCSY's Research Repository

Building HMM-SGMM Continuous Automatic Speech Recognition on Myanmar Web News

Show simple item record

dc.contributor.author Mon, Aye Nyein
dc.contributor.author Pa, Win Pa
dc.contributor.author Thu, Ye Kyaw
dc.date.accessioned 2019-07-15T04:56:02Z
dc.date.available 2019-07-15T04:56:02Z
dc.date.issued 2017-02-16
dc.identifier.uri http://onlineresource.ucsy.edu.mm/handle/123456789/895
dc.description.abstract Myanmar language is a tonal and analytic language. It can be considered as an under-resourced language because of its linguistic resource availability. Therefore, speech data collection is a very challenging task in building Myanmar automatic speech recognition. Today a lot of speech data are freely available on the Internet and we can collect it easily. Therefore, in this system, we take the advantages of Internet and we use daily news from the Web in building our speech corpus. In this paper, we will present about the task of data collection, the effect of Automatic Speech Recognition (ASR) performance according to amount of training data, language model size and error analysis of the experimental result. The experiments will be developed using Hidden Markov Model (HMM) with Gaussian Mixture Model (GMM) and Subspace Gaussian Mixture Model (SGMM). As a result, using our developed 5 hours training data, this system achieves word error rate (WER) of 7.6% on close test data and 31.9% on open test data with HMM-SGMM. en_US
dc.language.iso en en_US
dc.publisher Fifteenth International Conference on Computer Applications (ICCA 2017) en_US
dc.subject Automatic Speech Recognition (ASR) en_US
dc.subject speech corpus developing en_US
dc.subject News Domain en_US
dc.subject HMM-GMM en_US
dc.subject HMM-SGMM en_US
dc.subject Myanmar Language en_US
dc.title Building HMM-SGMM Continuous Automatic Speech Recognition on Myanmar Web News en_US
dc.type Article en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search Repository


My Account