Log in
Language:

MERAL Myanmar Education Research and Learning Portal

  • Top
  • Universities
  • Ranking
To
lat lon distance
To

Field does not validate



Index Link

Index Tree

Please input email address.

WEKO

One fine body…

WEKO

One fine body…

Item

{"_buckets": {"deposit": "7a4454d3-d466-4258-8c05-7628e13350c5"}, "_deposit": {"id": "4604", "owners": [], "pid": {"revision_id": 0, "type": "recid", "value": "4604"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/4604", "sets": ["user-ucsy"]}, "communities": ["ucsy"], "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "Building Speaker Identification Dataset for Noisy Conditions", "subitem_1551255648112": "en"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "Speech signal processing plays a crucial rolein any speech-related system whether AutomaticSpeech Recognition or Speaker Recognition orSpeech Synthesis or something else. Burmeselanguage can be considered as an under resourcedlanguage due to its linguistic resource availability.For building Burmese speaker identification system,the sufficient amount of speech data collection is avery challenging task in a short time. In order to gethigher data size, this paper analyzes that the gettinghigher duration of speech data actually combiningwith various noises encountering in oursurroundings. For increased noisy state speech data,we also used the voice activity detection (VAD)technique to acquire only the speaker specificinformation. For feature extraction, we used MFCC,Filter Banks and PLP techniques. The experimentswere developed with i-vector methods on GMM-UBMtogether with PLDA and presented the performanceof different data set in the form of EER with twomodels trained on clean and noisy data to prove thatthe developed speaker identification system is noiserobust."}]}, "item_1583103108160": {"attribute_name": "Keywords", "attribute_value_mlt": [{"interim": "Burmese Speaker Identification"}, {"interim": "noise robustness"}, {"interim": "VAD"}, {"interim": "MFCC"}, {"interim": "Filter Banks"}, {"interim": "PLP"}, {"interim": "GMMUBM"}, {"interim": "PLDA"}]}, "item_1583103120197": {"attribute_name": "Files", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_access", "date": [{"dateType": "Available", "dateValue": "2020-03-17"}], "displaytype": "preview", "download_preview_message": "", "file_order": 0, "filename": "Building Speaker Identification Dataset for Noisy Conditions.pdf", "filesize": [{"value": "299 Kb"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 299000.0, "url": {"url": "https://meral.edu.mm/record/4604/files/Building Speaker Identification Dataset for Noisy Conditions.pdf"}, "version_id": "2fc513dc-e62b-407f-baeb-b935972246e4"}]}, "item_1583103131163": {"attribute_name": "Journal articles", "attribute_value_mlt": [{"subitem_issue": "", "subitem_journal_title": "Proceedings of the Eighteenth International Conference On Computer Applications (ICCA 2020)", "subitem_pages": "", "subitem_volume": ""}]}, "item_1583103147082": {"attribute_name": "Conference papers", "attribute_value_mlt": [{"subitem_acronym": "", "subitem_c_date": "", "subitem_conference_title": "", "subitem_part": "", "subitem_place": "", "subitem_session": "", "subitem_website": ""}]}, "item_1583103211336": {"attribute_name": "Books/reports/chapters", "attribute_value_mlt": [{"subitem_book_title": "", "subitem_isbn": "", "subitem_pages": "", "subitem_place": "", "subitem_publisher": ""}]}, "item_1583103233624": {"attribute_name": "Thesis/dissertations", "attribute_value_mlt": [{"subitem_awarding_university": "", "subitem_supervisor(s)": [{"subitem_supervisor": ""}]}]}, "item_1583105942107": {"attribute_name": "Authors", "attribute_value_mlt": [{"subitem_authors": [{"subitem_authors_fullname": "Phyu, Win Lai Lai"}, {"subitem_authors_fullname": "Pa, Win Pa"}]}]}, "item_1583108359239": {"attribute_name": "Upload type", "attribute_value_mlt": [{"interim": "Publication"}]}, "item_1583108428133": {"attribute_name": "Publication type", "attribute_value_mlt": [{"interim": "Article"}]}, "item_1583159729339": {"attribute_name": "Publication date", "attribute_value": "2020-02-28"}, "item_1583159847033": {"attribute_name": "Identifier", "attribute_value": "978-1-7281-5925-6"}, "item_title": "Building Speaker Identification Dataset for Noisy Conditions", "item_type_id": "21", "owner": "1", "path": ["1597824273898"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000004604", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2020-03-17"}, "publish_date": "2020-03-17", "publish_status": "0", "recid": "4604", "relation": {}, "relation_version_is_last": true, "title": ["Building Speaker Identification Dataset for Noisy Conditions"], "weko_shared_id": -1}
  1. University of Computer Studies, Yangon
  2. Conferences

Building Speaker Identification Dataset for Noisy Conditions

http://hdl.handle.net/20.500.12678/0000004604
http://hdl.handle.net/20.500.12678/0000004604
3baf5851-b733-4563-ae18-dff7fb7eaa97
7a4454d3-d466-4258-8c05-7628e13350c5
None
Preview
Name / File License Actions
Building Building Speaker Identification Dataset for Noisy Conditions.pdf (299 Kb)
Publication type
Article
Upload type
Publication
Title
Title Building Speaker Identification Dataset for Noisy Conditions
Language en
Publication date 2020-02-28
Authors
Phyu, Win Lai Lai
Pa, Win Pa
Description
Speech signal processing plays a crucial rolein any speech-related system whether AutomaticSpeech Recognition or Speaker Recognition orSpeech Synthesis or something else. Burmeselanguage can be considered as an under resourcedlanguage due to its linguistic resource availability.For building Burmese speaker identification system,the sufficient amount of speech data collection is avery challenging task in a short time. In order to gethigher data size, this paper analyzes that the gettinghigher duration of speech data actually combiningwith various noises encountering in oursurroundings. For increased noisy state speech data,we also used the voice activity detection (VAD)technique to acquire only the speaker specificinformation. For feature extraction, we used MFCC,Filter Banks and PLP techniques. The experimentswere developed with i-vector methods on GMM-UBMtogether with PLDA and presented the performanceof different data set in the form of EER with twomodels trained on clean and noisy data to prove thatthe developed speaker identification system is noiserobust.
Keywords
Burmese Speaker Identification, noise robustness, VAD, MFCC, Filter Banks, PLP, GMMUBM, PLDA
Identifier 978-1-7281-5925-6
Journal articles
Proceedings of the Eighteenth International Conference On Computer Applications (ICCA 2020)
Conference papers
Books/reports/chapters
Thesis/dissertations
Back
0
0
views
downloads
See details
Views Downloads

Versions

Ver.1 2020-09-01 15:10:41.677629
Show All versions

Share

Mendeley Twitter Facebook Print Addthis

Export

OAI-PMH
  • OAI-PMH DublinCore
Other Formats
  • JSON

Confirm


Back to MERAL


Back to MERAL