Can we Generate Emotional Pronunciations for Expressive Speech Synthesis?

Marie Tahon (1) , Gwénolé Lecorvé (2) , Damien Lolive (2)

1 LIUM - Laboratoire d'Informatique de l'Université du Mans
2 EXPRESSION - Expressiveness in Human Centered Data/Media

In the field of expressive speech synthesis, a lot of work has been conducted on suprasegmental prosodic features while few has been done on pronunciation variants. However, prosody is highly related to the sequence of phonemes to be expressed. This article raises two issues in the generation of emotional pronunciations for TTS systems. The first issue consists in designing an automatic pronunciation generation method from text, while the second issue addresses the very existence of emotional pronunciations through experiments conducted on emotional speech. To do so, an innovative pronunciation adaptation method which automatically adapts canonical phonemes first to those labeled in the corpus used to create a synthetic voice, then to those labeled in an expressive corpus, is presented. This method consists in training conditional random fields pronunciation models with prosodic, linguistic, phonological and articulatory features. The analysis of emotional pronunciations reveals strong dependencies between prosody and phoneme assimilation or elisions. According to perception tests, the double adaptation allows to synthesize expressive speech samples of good quality, but emotion-specific pronunciations are too subtle to be perceived by testers.

Mots clés: Expressive speech synthesis; emotion; pronunciation adaptation; conditional random fields

Domaines: Intelligence artificielle [cs.AI]; Informatique et langage [cs.CL]

Marie Tahon, Gwénolé Lecorvé, Damien Lolive. Can we Generate Emotional Pronunciations for Expressive Speech Synthesis?. IEEE Transactions on Affective Computing, 2020, 11 (4), pp.684-695. ⟨10.1109/TAFFC.2018.2828429⟩. ⟨hal-01802463⟩