Prodorshok I: a Bengali isolated speech dataset for voice-based assistive technologies: a comparative analysis of the effects of data augmentation on HMM-GMM and DNN classifiers

Simple item page
bracu.type.groupResearch Publications
datacite.rightsOpen Access
dc.contributor.authorReza, Mohi
dc.contributor.authorRashid, Warida
dc.contributor.authorMostakim, Moin
dc.contributor.departmentDepartment of Computer Science and Engineering
dc.date.accessioned2026-08-13T09:09:56Z
dc.date.available2026-08-13T09:09:56Z
dc.date.issued2018-02-09
dc.description.abstractProdorshok I is a Bengali isolated word dataset tailored to help create speaker-independent, voice-command driven automated speech recognition (ASR) based assistive technologies to help improve human-computer interaction (HCI). This paper presents the results of an objective analysis that was undertaken using a subset of words from Prodorshok I to assess its reliability in ASR systems that utilize Hidden Markov Models (HMM) with Gaussian emissions and Deep Neural Networks (DNN). The results show that simple data augmentation involving a small pitch shift can make surprisingly tangible improvements to accuracy levels in speech recognition.
dc.description.versionPublished
dc.format.extent396-399
dc.identifier.citationM. Reza, W. Rashid and M. Mostakim, "Prodorshok I: A bengali isolated speech dataset for voice-based assistive technologies: A comparative analysis of the effects of data augmentation on HMM-GMM and DNN classifiers," 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), Dhaka, Bangladesh, 2017, pp. 396-399, doi: 10.1109/R10-HTC.2017.8288983.
dc.identifier.doi10.1109/R10-HTC.2017.8288983
dc.identifier.issn9781538621752
dc.identifier.other2-s2.0-85047405963
dc.identifier.urihttps://hdl.handle.net/10361/29046
dc.language.isoen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.hasversion10.1109/R10-HTC.2017.8288983
dc.relation.ispartof5th IEEE Region 10 Humanitarian Technology Conference 2017 R10 Htc 2017
dc.relation.ispartofseries5th IEEE Region 10 Humanitarian Technology Conference 2017 R10 Htc 2017
dc.relation.urihttps://ieeexplore.ieee.org/document/8288983
dc.rightsfalse
dc.subjectAssistive technology
dc.subjectAutomatic speech recognition
dc.subjectBengali
dc.subjectDeep neural network
dc.subjectGaussian mixture model
dc.subjectHidden markov Model
dc.subjectHuman computer interaction
dc.subject.lcshAutomatic speech recognition.
dc.subject.lcshBengali language.
dc.subject.lcshHuman-computer interaction.
dc.titleProdorshok I: a Bengali isolated speech dataset for voice-based assistive technologies: a comparative analysis of the effects of data augmentation on HMM-GMM and DNN classifiers
dc.typeConference Proceeding
oaire.citation.volume2018-January
person.affiliation.nameBRAC University
person.affiliation.nameBRAC University
person.affiliation.nameBRAC University
person.identifier.scopus-author-id58407893900
person.identifier.scopus-author-id57202199542
person.identifier.scopus-author-id55758417600

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Prodorshok_I_A_bengali_isolated_speech_dataset_for_voice-based_assistive_technologies_A_comparative_analysis_of_the_effects_of_data_augmentation_on_HMM-GMM_and_DNN_classifiers.pdf
Size:
415.16 KB
Format:
Adobe Portable Document Format
Download

License bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Scholarly Indexed Publications