Investigation of the Effect of LSTM Hyperparameters on Speech Recognition Performance

Basit Öğe Kaydı
dc.contributor.authorDokuz, Yeşim
dc.contributor.authorTüfekçi, Zekeriya
dc.date.accessioned2024-11-07T13:19:01Z
dc.date.available2024-11-07T13:19:01Z
dc.date.issued2020
dc.departmentNiğde Ömer Halisdemir Üniversitesi
dc.description.abstractWith the recent advances in hardware technologies and computational methods, computers became more powerful for analyzingdifficult tasks, such as speech recognition and image processing. Speech recognition is the task of extraction of text representation ofa speech signal using computational or analytical methods. Speech recognition is a challenging problem due to variations in accents and languages, powerful hardware requirements, big dataset needs for generating accurate models, and environmental factors thataffect signal quality. Recently, with the increasing processing ability of hardware devices, such as Graphical Processing Units, deeplearning methods became more prevalent and state-of-the-art method for speech recognition, especially Recurrent Neural Networks(RNNs) and Long-Short Term Memory (LSTMs) networks which is a variant of RNNs. In the literature, RNNs and LSTMs are usedfor speech recognition and the applications of speech recognition with various parameters, i.e. number of layers, number of hiddenunits, and batch size. It is not investigated that how the parameter values of the literature are selected and whether these values couldbe used in future studies. In this study, we investigated the effect of LSTMs hyperparameters on speech recognition performance interms of error rates and deep architecture cost. Each parameter is investigated separately while other parameters remain constant andthe effect of each parameter is observed on a speech corpus. Experimental results show that each parameter has its specific values forthe selected number of training instances to provide lower error rates and better speech recognition performance. It is shown in thisstudy that before selecting appropriate values for each LSTM parameters, there should be several experiments performed on thespeech corpus to find the most eligible value for each parameter.
dc.identifier.doi10.31590/ejosat.araconf21
dc.identifier.endpage168
dc.identifier.issn2148-2683
dc.identifier.issueEjosat Özel Sayı 2020 (ARACONF)
dc.identifier.startpage161
dc.identifier.trdizinid364761
dc.identifier.urihttps://doi.org/10.31590/ejosat.araconf21
dc.identifier.urihttps://search.trdizin.gov.tr/tr/yayin/detay/364761
dc.identifier.urihttps://hdl.handle.net/11480/12828
dc.identifier.volume0
dc.indekslendigikaynakTR-Dizin
dc.language.isoen
dc.relation.ispartofAvrupa Bilim ve Teknoloji Dergisi
dc.relation.publicationcategoryMakale - Ulusal Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_20241107
dc.subjectBilgisayar Bilimleri
dc.subjectYazılım Mühendisliği
dc.subjectBilgisayar Bilimleri
dc.subjectSibernitik
dc.subjectBilgisayar Bilimleri
dc.subjectBilgi Sistemleri
dc.subjectBilgisayar Bilimleri
dc.subjectDonanım ve Mimari
dc.subjectBilgisayar Bilimleri
dc.subjectTeori ve Metotlar
dc.subjectAkustik
dc.subjectBilgisayar Bilimleri
dc.subjectYapay Zeka
dc.titleInvestigation of the Effect of LSTM Hyperparameters on Speech Recognition Performance
dc.typeArticle

Dosyalar

Koleksiyon

TR-Dizin İndeksli Yayınlar Koleksiyonu