Speaker-independent raw waveform model for glottal excitation

Loading...
Thumbnail Image

Access rights

openAccess
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Major/Subject

Mcode

Degree programme

Language

en

Pages

Series

Proceedings of Interspeech, pp. 2012-2016, Interspeech - Annual Conference of the International Speech Communication Association

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.

Description

Other note

Citation

Juvela, L, Tsiaras, V, Bollepalli, B, Airaksinen, M, Yamagishi, J & Alku, P 2018, Speaker-independent raw waveform model for glottal excitation. in Proceedings of Interspeech. Interspeech - Annual Conference of the International Speech Communication Association, International Speech Communication Association (ISCA), pp. 2012-2016, Interspeech, Hyderabad, India, 02/09/2018. https://doi.org/10.21437/Interspeech.2018-1635