Back to Search Start Over

Exemplar-based Speech Waveform Generation

Authors :
Felipe Espic
Simon King
Cassia Valentini-Botinhao
Oliver Watts
Source :
INTERSPEECH, Watts, O, Valentini Botinhao, C, Espic calderón, F & King, S 2018, Exemplar-based Speech Waveform Generation . in Interspeech 2018 . Hyderabad, India, pp. 2022-2026, Interspeech 2018, Hyderabad, India, 2/09/18 . https://doi.org/10.21437/Interspeech.2018-1857
Publication Year :
2018
Publisher :
ISCA, 2018.

Abstract

This paper presents a simple but effective method for generating speech waveforms by selecting small units of stored speech to match a low-dimensional target representation. The method is designed as a drop-in replacement for the vocoder in a deep neural network-based text-to-speech system. Most previous work on hybrid unit selection waveform generation relies on phonetic annotation for determining unit boundaries, or for specifying target cost, or for candidate preselection. In contrast, our waveform generator requires no phonetic information, annotation, or alignment. Unit boundaries are determined by epochs, and spectral analysis provides representations which are compared directly with target features at runtime. As in unit selection, we minimise a combination of target cost and join cost, but find that greedy left-to-right nearest-neighbour search gives similar results to dynamic programming. The method is fast and can generate the waveform incrementally. We use publicly available data and provide a permissively-licensed open source toolkit for reproducing our results.

Details

Database :
OpenAIRE
Journal :
Interspeech 2018
Accession number :
edsair.doi.dedup.....0b19e9c97d4ffc4fd51e277c70451d62