Effects of training data variety in generating glottal pulses from acoustic features with DNNs

Manu Airaksinen, Paavo Alku

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

2 Citations (Scopus)
311 Downloads (Pure)

Abstract

Glottal volume velocity waveform, the acoustical excitation of voiced speech, cannot be acquired through direct measurements in normal production of continuous speech. Glottal inverse filtering (GIF), however, can be used to estimate the glottal flow from recorded speech signals. Unfortunately, the usefulness of GIF algorithms is limited since they are sensitive to noise and call for high-quality recordings. Recently, efforts have been taken to expand the use of GIF by training deep neural networks (DNNs) to learn a statistical mapping between frame-level acoustic features and glottal pulses estimated by GIF. This framework has been successfully utilized in statistical speech synthesis in the form of the GlottDNN vocoder which uses a DNN to generate glottal pulses to be used as the synthesizer’s excitation waveform. In this study, we investigate how the DNN-based generation of glottal pulses is affected by training data variety. The evaluation is done using both objective measures as well as subjective listening tests of synthetic speech. The results suggest that the performance of the glottal pulse generation with DNNs is affected particularly by how well the training corpus suits GIF: processing low-pitched male speech and sustained phonations shows better performance than processing high-pitched female voices or continuous speech.
Original languageEnglish
Title of host publicationProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
PublisherInternational Speech Communication Association (ISCA)
Pages3946-3950
Number of pages5
Volume2017-August
DOIs
Publication statusPublished - Aug 2017
MoE publication typeA4 Conference publication
EventInterspeech - Stockholm, Sweden
Duration: 20 Aug 201724 Aug 2017
Conference number: 18
http://www.interspeech2017.org/

Publication series

NameInterspeech: Annual Conference of the International Speech Communication Association
ISSN (Electronic)1990-9772

Conference

ConferenceInterspeech
Country/TerritorySweden
CityStockholm
Period20/08/201724/08/2017
Internet address

Keywords

  • glottal inverse filtering
  • speech synthesis

Fingerprint

Dive into the research topics of 'Effects of training data variety in generating glottal pulses from acoustic features with DNNs'. Together they form a unique fingerprint.

Cite this