Speaker-independent raw waveform model for glottal excitation

Lauri Juvela, Vassilis Tsiaras, Bajibabu Bollepalli, Manu Airaksinen, Junichi Yamagishi, Paavo Alku

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

22 Citations (Scopus)
142 Downloads (Pure)

Abstract

Recent speech technology research has seen a growing interest in using WaveNets as statistical vocoders, i.e., generating speech waveforms from acoustic features. These models have been shown to improve the generated speech quality over classical vocoders in many tasks, such as text-to-speech synthesis and voice conversion. Furthermore, conditioning WaveNets with acoustic features allows sharing the waveform generator model across multiple speakers without additional speaker codes. However, multi-speaker WaveNet models require large amounts of training data and computation to cover the entire acoustic space. This paper proposes leveraging the source-filter model of speech production to more effectively train a speaker-independent waveform generator with limited resources. We present a multi-speaker ’GlotNet’ vocoder, which utilizes a WaveNet to generate glottal excitation waveforms, which are then used to excite the corresponding vocal tract filter to produce speech. Listening tests show that the proposed model performs favourably to a direct WaveNet vocoder trained with the same model architecture and data.
Original languageEnglish
Title of host publicationProceedings of Interspeech
PublisherInternational Speech Communication Association
Pages2012-2016
DOIs
Publication statusPublished - 2 Sep 2018
MoE publication typeA4 Article in a conference publication
EventInterspeech - Hyderabad International Convention Centre, Hyderabad, India
Duration: 2 Sep 20186 Sep 2018
http://interspeech2018.org/

Publication series

NameInterspeech - Annual Conference of the International Speech Communication Association
ISSN (Electronic)2308-457X

Conference

ConferenceInterspeech
CountryIndia
CityHyderabad
Period02/09/201806/09/2018
Internet address

Keywords

  • Glottal source generation
  • WaveNet
  • mixture density network

Fingerprint Dive into the research topics of 'Speaker-independent raw waveform model for glottal excitation'. Together they form a unique fingerprint.

Cite this