Augmented CycleGANs for continuous scale normal-to-Lombard speaking style conversion

Loading...
Thumbnail Image
Journal Title
Journal ISSN
Volume Title
Conference article in proceedings
This publication is imported from Aalto University research portal.
View publication in the Research portal
View/Open full text file from the Research portal
Date
2019
Major/Subject
Mcode
Degree programme
Language
en
Pages
2838-2842
Series
Proceedings of Interspeech, Interspeech - Annual Conference of the International Speech Communication Association
Abstract
Lombard speech is a speaking style associated with increased vocal effort that is naturally used by humans to improve intelligibility in the presence of noise. It is hence desirable to have a system capable of converting speech from normal to Lombard style. Moreover, it would be useful if one could adjust the degree of Lombardness in the converted speech so that the system is more adaptable to different noise environments. In this study, we propose the use of recently developed Augmented cycle-consistent adversarial networks (Augmented CycleGANs) for conversion between normal and Lombard speaking styles. The proposed system gives a smooth control on the degree of Lombardness of the mapped utterances by traversing through different points in the latent space of the trained model. We utilize a parametric approach that uses the Pulse Model in Log domain (PML) vocoder to extract features from normal speech that are then mapped to Lombard-style features using the Augmented CycleGAN. Finally, the mapped features are converted to Lombard speech with PML. The model is trained on multi-language data recorded in different noise conditions, and we compare its effectiveness to a previously proposed CycleGAN system in experiments for intelligibility and quality of mapped speech.
Description
Keywords
Augmented CycleGAN, Lombard speech, Pulse-model in log domain vocoder, Style conversion, Vocal effort
Other note
Citation
Seshadri , S , Juvela , L , Alku , P & Räsänen , O 2019 , Augmented CycleGANs for continuous scale normal-to-Lombard speaking style conversion . in Proceedings of Interspeech . Interspeech - Annual Conference of the International Speech Communication Association , International Speech Communication Association (ISCA) , pp. 2838-2842 , Interspeech , Graz , Austria , 15/09/2019 . https://doi.org/10.21437/Interspeech.2019-1681