Mini-batch sample selection strategies for deep learning based speech recognition

Basit Öğe Kaydı
dc.contributor.authorDokuz, Yesim
dc.contributor.authorTufekci, Zekeriya
dc.date.accessioned2024-11-07T13:31:21Z
dc.date.available2024-11-07T13:31:21Z
dc.date.issued2021
dc.departmentNiğde Ömer Halisdemir Üniversitesi
dc.description.abstractWith the use of deep learning technologies, speech recognition systems gained more success and human-computer interactions became more prevalent. Deep learning based speech recognition systems are getting more attention and are having tremendous success in all areas of speech recognition, such as voice search, mobile communication, and personal digital assistance. However, speech recognition is still challenging due to hardness of adapting new languages, difficulty in handling variations in speech datasets, and overcoming distorting factors. Deep learning systems have the ability to overcome these challenges using high-level abstractions in the datasets by using a deep graph with multiple processing layers using training algorithms, such as gradient descent optimization. In this study, a variant of gradient descent optimization, mini-batch gradient descent is used. We proposed four strategies for selecting mini-batch samples to represent variations of each feature in the dataset for speech recognition tasks to increase model performance of deep learning based speech recognition. For this purpose, gender and accent adjusted strategies are proposed for selecting mini-batch samples. The experiments show that proposed strategies perform better in comparison with standard mini-batch sample selection strategy. (C) 2020 Elsevier Ltd. All rights reserved.
dc.identifier.doi10.1016/j.apacoust.2020.107573
dc.identifier.issn0003-682X
dc.identifier.issn1872-910X
dc.identifier.scopus2-s2.0-85089352303
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1016/j.apacoust.2020.107573
dc.identifier.urihttps://hdl.handle.net/11480/14793
dc.identifier.volume171
dc.identifier.wosWOS:000580649900024
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherElsevier Sci Ltd
dc.relation.ispartofApplied Acoustics
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20241106
dc.subjectMini-batch gradient descent
dc.subjectSample selection strategies
dc.subjectDeep learning
dc.subjectSpeech recognition
dc.subjectLSTM
dc.titleMini-batch sample selection strategies for deep learning based speech recognition
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu