Log in
Language:

MERAL Myanmar Education Research and Learning Portal

  • Top
  • Universities
  • Ranking


Index Link

Index Tree

  • RootNode

Please input email address.

WEKO

One fine body…

WEKO

One fine body…

Item

{"_buckets": {"deposit": "3419ad9e-ff38-464c-8a9d-347940ac5a6c"}, "_deposit": {"id": "3443", "owners": [], "pid": {"revision_id": 0, "type": "recid", "value": "3443"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/3443", "sets": ["user-ucsy"]}, "communities": ["ucsy"], "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "Myanmar Speech Classification Using Transfer Learning for Image Classification", "subitem_1551255648112": "en"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "In this paper, our research on speechclassification using an image classification approachis discussed for the Myanmar language. We tested themethod for Myanmar consonants, vowels, and words,on our recorded database of 22-consonant, 12-vowel,and 54-word sound classes, containing spectrogramsof Myanmar speech. Because Myanmar language istonal, the sounds are very similar for preciseclassification based on audio features, while thevisual representations differ. Therefore, it isimportant to consider the visual representations ofaudio in classifying the Myanmar language. In thisstudy, we treated Myanmar speeches with aconvolutional neural network model (Inception-v3) tofit spectrogram images, performing transfer learningfrom pre-trained weights on ImageNet. Validationaccuracies of 60.70%, 73.20%, and 94.60% wereachieved for the consonant, vowel, and word-levelclassifications, respectively. In order to determine theretrained model performance, both closed and opentesting were conducted. Although our experiment wasdistinct from other traditional audio classificationmethods, promising results were obtained for the firstexploration of Myanmar speech classification usingtransfer learning for image classification. In fact,these experimental results were attained usingGoogle’s Inception-v3 model, constructed withdifferent image domains. Therefore, the research andresults demonstrate that it is possible to performMyanmar speech classification."}]}, "item_1583103108160": {"attribute_name": "Keywords", "attribute_value": []}, "item_1583103120197": {"attribute_name": "Files", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_access", "date": [{"dateType": "Available", "dateValue": "2019-07-22"}], "displaytype": "preview", "download_preview_message": "", "file_order": 0, "filename": "ICCA 2019 Proceedings Book-pages-143-151.pdf", "filesize": [{"value": "1277 Kb"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 1277000.0, "url": {"url": "https://meral.edu.mm/record/3443/files/ICCA 2019 Proceedings Book-pages-143-151.pdf"}, "version_id": "8bc176a0-229f-4090-933d-b5ccfaf8ef9c"}]}, "item_1583103131163": {"attribute_name": "Journal articles", "attribute_value_mlt": [{"subitem_issue": "", "subitem_journal_title": "Seventeenth International Conference on Computer Applications(ICCA 2019)", "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": "Khin, Ou Ou"}, {"subitem_authors_fullname": "Thu, Ye Kyaw"}, {"subitem_authors_fullname": "Sakata, Tadashi"}, {"subitem_authors_fullname": "SAGISAKA, Yoshinori"}, {"subitem_authors_fullname": "Ueda, Yuichi"}]}]}, "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": "2019-02-27"}, "item_1583159847033": {"attribute_name": "Identifier", "attribute_value": "http://onlineresource.ucsy.edu.mm/handle/123456789/1192"}, "item_title": "Myanmar Speech Classification Using Transfer Learning for Image Classification", "item_type_id": "21", "owner": "1", "path": ["1597824273898"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000003443", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2019-07-22"}, "publish_date": "2019-07-22", "publish_status": "0", "recid": "3443", "relation": {}, "relation_version_is_last": true, "title": ["Myanmar Speech Classification Using Transfer Learning for Image Classification"], "weko_shared_id": -1}
  1. University of Computer Studies, Yangon
  2. Conferences

Myanmar Speech Classification Using Transfer Learning for Image Classification

http://hdl.handle.net/20.500.12678/0000003443
http://hdl.handle.net/20.500.12678/0000003443
6575ef03-0341-4d12-ba30-6bfd904813d1
3419ad9e-ff38-464c-8a9d-347940ac5a6c
None
Preview
Name / File License Actions
ICCA ICCA 2019 Proceedings Book-pages-143-151.pdf (1277 Kb)
Back
0
0
views
downloads
See details
Views Downloads

Versions

Ver.1 2020-09-01 12:30:42.535608
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