Show simple item record

dc.contributor.authorKato, Akihiro
dc.contributor.authorKinnunen, Tomi
dc.contributor.editor-
dc.date.accessioned2018-12-18T13:35:30Z
dc.date.available2018-12-18T13:35:30Z
dc.date.issued2018
dc.identifier.urihttps://erepo.uef.fi/handle/123456789/7213
dc.description.abstractThe fundamental frequency (F0) contour of speech is a key aspect to represent speech prosody that finds use in speech and spoken language analysis such as voice conversion and speech synthesis as well as speaker and language identification. This work proposes new methods to estimate the F0 contour of speech using deep neural networks (DNNs) and recurrent neural networks (RNNs). They are trained using supervised learning with the ground truth of F0 contours. The latest prior research addresses this problem first as a frame-by-frame-classification problem followed by sequence tracking using deep neural network hidden Markov model (DNN-HMM) hybrid architecture. This study, however, tackles the problem as a regression problem instead, in order to obtain F0 contours with higher frequency resolution from clean an noisy speech. Experiments using PTDB-TUG corpus contaminated with additive noise (NOISEX-92) show the proposed method improves gross pitch error (GPE) by more than 25 % at signal-to-noise ratios (SNRs) between -10 dB and +10 dB as compared with one of the most noise-robust F0 trackers, PEFAC. Furthermore, the performance on fine pitch error (FPE) is improved by approximately 20 % against a state-of-the-art DNN-HMM-based approach.
dc.language.isoenglanti
dc.publisherISCA
dc.relation.ispartofProceedings of Odyssey 2018: The Speaker and Language Recognition Workshop, 26-29 June 2018, Les Sables d'Olonne, France
dc.relation.urihttp://dx.doi.org/10.21437/Odyssey.2018-39
dc.rightsAll rights reserved
dc.titleA Regression Model of Recurrent Deep Neural Networks for Noise Robust Estimation of the Fundamental Frequency Contour of Speech
dc.description.versionpublished version
dc.contributor.departmentSchool of Computing, activities
uef.solecris.id56162412en
dc.type.publicationArtikkelit ja abstraktit tieteellisissä konferenssijulkaisuissa
dc.rights.accessrights© ISCA
dc.relation.doi10.21437/Odyssey.2018-39
dc.description.reviewstatuspeerReviewed
dc.format.pagerange275-282
dc.relation.issn2312-2846
dc.relation.numberinseries2018
dc.rights.accesslevelopenAccess
dc.type.okmA4
uef.solecris.openaccessOpen access -julkaisukanavassa ilmestynyt julkaisu


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record