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

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


Research units

  • Tampere University


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.


Original languageEnglish
Title of host publicationProceedings of Interspeech
Publication statusPublished - 2019
MoE publication typeA4 Article in a conference publication
EventInterspeech - Graz, Austria
Duration: 15 Sep 201919 Sep 2019

Publication series

NameInterspeech - Annual Conference of the International Speech Communication Association
ISSN (Electronic)2308-457X


Internet address

    Research areas

  • Augmented CycleGAN, Lombard speech, Pulse-model in log domain vocoder, Style conversion, Vocal effort

Download statistics

No data available

ID: 34996622