UCSY's Research Repository

Building Speaker Identification Dataset for Noisy Conditions

Show simple item record

dc.contributor.author Phyu, Win Lai Lai
dc.contributor.author Pa, Win Pa
dc.date.accessioned 2020-03-17T12:18:16Z
dc.date.available 2020-03-17T12:18:16Z
dc.date.issued 2020-02-28
dc.identifier.isbn 978-1-7281-5925-6
dc.identifier.uri http://onlineresource.ucsy.edu.mm/handle/123456789/2522
dc.description.abstract Speech signal processing plays a crucial role in any speech-related system whether Automatic Speech Recognition or Speaker Recognition or Speech Synthesis or something else. Burmese language can be considered as an under resourced language due to its linguistic resource availability. For building Burmese speaker identification system, the sufficient amount of speech data collection is a very challenging task in a short time. In order to get higher data size, this paper analyzes that the getting higher duration of speech data actually combining with various noises encountering in our surroundings. For increased noisy state speech data, we also used the voice activity detection (VAD) technique to acquire only the speaker specific information. For feature extraction, we used MFCC, Filter Banks and PLP techniques. The experiments were developed with i-vector methods on GMM-UBM together with PLDA and presented the performance of different data set in the form of EER with two models trained on clean and noisy data to prove that the developed speaker identification system is noise robust. en_US
dc.language.iso en en_US
dc.publisher Proceedings of the Eighteenth International Conference On Computer Applications (ICCA 2020) en_US
dc.subject Burmese Speaker Identification en_US
dc.subject noise robustness en_US
dc.subject VAD en_US
dc.subject MFCC en_US
dc.subject Filter Banks en_US
dc.subject PLP en_US
dc.subject GMMUBM en_US
dc.subject PLDA en_US
dc.title Building Speaker Identification Dataset for Noisy Conditions 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