Formant tracking using quasi-closed phase forward-backward linear prediction analysis and deep neural networks

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorGowda, Dhananjaya
dc.contributor.authorBollepalli, Bajibabu
dc.contributor.authorKadiri, Sudarsana
dc.contributor.authorAlku, Paavo
dc.contributor.departmentDept Signal Process and Acoust
dc.contributor.departmentSpeech Communication Technology
dc.date.accessioned2021-12-08T07:31:05Z
dc.date.available2021-12-08T07:31:05Z
dc.date.issued2021
dc.description.abstractFormant tracking is investigated in this study by using trackers based on dynamic programming (DP) and deep neural nets (DNNs). Using the DP approach, six formant estimation methods were first compared. The six methods include linear prediction (LP) algorithms, weighted LP algorithms and the recently developed quasi-closed phase forward-backward (QCP-FB) method. QCP-FB gave the best performance in the comparison. Therefore, a novel formant tracking approach, which combines benefits of deep learning and signal processing based on QCP-FB, was proposed. In this approach, the formants predicted by a DNN-based tracker from a speech frame are refined using the peaks of the all-pole spectrum computed by QCP-FB from the same frame. Results show that the proposed DNN-based tracker performed better both in detection rate and estimation error for the lowest three formants compared to reference formant trackers. Compared to the popular Wavesurfer, for example, the proposed tracker gave a reduction of 29%, 48%, and 35% inthe estimation error for the lowest three formants, respectively.en
dc.description.versionPeer revieweden
dc.format.extent10
dc.format.extent151631-151640
dc.format.mimetypeapplication/pdf
dc.identifier.citationGowda , D , Bollepalli , B , Kadiri , S & Alku , P 2021 , ' Formant tracking using quasi-closed phase forward-backward linear prediction analysis and deep neural networks ' , IEEE Access , vol. 9 , pp. 151631-151640 . https://doi.org/10.1109/ACCESS.2021.3126280en
dc.identifier.doi10.1109/ACCESS.2021.3126280
dc.identifier.issn2169-3536
dc.identifier.otherPURE UUID: 41ea8bfd-916c-49ab-a466-77e34fe57a4f
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/41ea8bfd-916c-49ab-a466-77e34fe57a4f
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/76582163/Formant_Tracking_Using_Quasi_Closed_Phase_Forward_Backward_Linear_Prediction_Analysis_and_Deep_Neural_Networks.pdf
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/111447
dc.identifier.urnURN:NBN:fi:aalto-2021120810591
dc.language.isoenen
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartofseriesIEEE Accessen
dc.relation.ispartofseriesVolume 9en
dc.rightsopenAccessen
dc.subject.keywordSpeech analysis
dc.subject.keywordformant tracking
dc.subject.keywordlinear prediction
dc.subject.keyworddynamic programming
dc.subject.keyworddeep neural network
dc.titleFormant tracking using quasi-closed phase forward-backward linear prediction analysis and deep neural networksen
dc.typeA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessäfi
dc.type.versionpublishedVersion
Files