Speaker-independent raw waveform model for glottal excitation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Details

Original languageEnglish
Title of host publicationProceedings of Interspeech
PublisherInternational Speech Communication Association
Pages2012-2016
StatePublished - 2 Sep 2018
MoE publication typeA4 Article in a conference publication
EventAnnual Conference of the International Speech Communication Association - Hyberabad, India
Duration: 2 Sep 20186 Sep 2018

Publication series

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

Conference

ConferenceAnnual Conference of the International Speech Communication Association
Abbreviated titleINTERSPEECH
CountryIndia
CityHyberabad
Period02/09/201806/09/2018

Researchers

Research units

  • University of Crete
  • National Institute of Informatics

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.

    Research areas

  • Glottal source generation, WaveNet, mixture density network

ID: 28748306