Home Publications Research Grants Inventions & Patents Awards Additional Research Activities Faculties & Institutions Research Areas

Analysis by adversarial synthesis - A novel approach for speech vocoding

Mustafa A, Biswas A, Bergler C, Schottenhamml J, Maier A (2019)

---

Publication Type: Conference contribution

Publication year: 2019

Publisher: International Speech Communication Association

Book Volume: 2019-September

Pages Range: 191-195

Conference Proceedings Title: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Event location: Graz, AUT

DOI: 10.21437/Interspeech.2019-1195

Abstract

Classical parametric speech coding techniques provide a compact representation for speech signals. This affords a very low transmission rate but with a reduced perceptual quality of the reconstructed signals. Recently, autoregressive deep generative models such as WaveNet and SampleRNN have been used as speech vocoders to scale up the perceptual quality of the reconstructed signals without increasing the coding rate. However, such models suffer from a very slow signal generation mechanism due to their sample-by-sample modelling approach. In this work, we introduce a new methodology for neural speech vocoding based on generative adversarial networks (GANs). A fake speech signal is generated from a very compressed representation of the glottal excitation using conditional GANs as a deep generative model. This fake speech is then refined using the LPC parameters of the original speech signal to obtain a natural reconstruction. The reconstructed speech waveforms based on this approach show a higher perceptual quality than the classical vocoder counterparts according to subjective and objective evaluation scores for a dataset of 30 male and female speakers. Moreover, the usage of GANs enables to generate signals in one-shot compared to autoregressive generative models. This makes GANs promising for exploration to implement high-quality neural vocoders.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Mustafa, A., Biswas, A., Bergler, C., Schottenhamml, J., & Maier, A. (2019). Analysis by adversarial synthesis - A novel approach for speech vocoding. In Gernot Kubin, Thomas Hain, Bjorn Schuller, Dina El Zarka, Petra Hodl (Eds.), Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (pp. 191-195). Graz, AUT: International Speech Communication Association.

MLA:

Mustafa, Ahmed, et al. "Analysis by adversarial synthesis - A novel approach for speech vocoding." Proceedings of the 20th Annual Conference of the International Speech Communication Association: Crossroads of Speech and Language, INTERSPEECH 2019, Graz, AUT Ed. Gernot Kubin, Thomas Hain, Bjorn Schuller, Dina El Zarka, Petra Hodl, International Speech Communication Association, 2019. 191-195.

BibTeX: Download