Normal-to-Lombard adaptation of speech synthesis using long short-term memory recurrent neural networks

No Thumbnail Available
Access rights
openAccess
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
Date
2019-07-01
Major/Subject
Mcode
Degree programme
Language
en
Pages
12
64-75
Series
Speech Communication, Volume 110
Abstract
In this article, three adaptation methods are compared based on how well they change the speaking style of a neural network based text-to-speech (TTS) voice. The speaking style conversion adopted here is from normal to Lombard speech. The selected adaptation methods are: auxiliary features (AF), learning hidden unit contribution (LHUC), and fine-tuning (FT). Furthermore, four state-of-the-art TTS vocoders are compared in the same context. The evaluated vocoders are: GlottHMM, GlottDNN, STRAIGHT, and pulse model in log-domain (PML). Objective and subjective evaluations were conducted to study the performance of both the adaptation methods and the vocoders. In the subjective evaluations, speaking style similarity and speech intelligibility were assessed. In addition to acoustic model adaptation, phoneme durations were also adapted from normal to Lombard with the FT adaptation method. In objective evaluations and speaking style similarity tests, we found that the FT method outperformed the other two adaptation methods. In speech intelligibility tests, we found that there were no significant differences between vocoders although the PML vocoder showed slightly better performance compared to the three other vocoders.
Description
Keywords
Lombard, Auxiliary features, LHUC, Fine-tuning, LSTM, Adaptation, TTS
Other note
Citation
Bollepalli, B, Juvela, L, Airaksinen, M, Valentini-Botinhao, C & Alku, P 2019, ' Normal-to-Lombard adaptation of speech synthesis using long short-term memory recurrent neural networks ', Speech Communication, vol. 110, pp. 64-75 . https://doi.org/10.1016/j.specom.2019.04.008