Speaker-independent raw waveform model for glottal excitation

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussavertaisarvioitu

Tutkijat

Organisaatiot

  • University of Crete
  • National Institute of Informatics

Kuvaus

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.

Yksityiskohdat

AlkuperäiskieliEnglanti
OtsikkoProceedings of Interspeech
TilaJulkaistu - 2 syyskuuta 2018
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaInterspeech - Hyberabad, Intia
Kesto: 2 syyskuuta 20186 syyskuuta 2018

Julkaisusarja

NimiInterspeech - Annual Conference of the International Speech Communication Association
ISSN (elektroninen)2308-457X

Conference

ConferenceInterspeech
MaaIntia
KaupunkiHyberabad
Ajanjakso02/09/201806/09/2018

Lataa tilasto

Ei tietoja saatavilla

ID: 28748306