Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Expressive speech synthesis using sentiment embeddings

Autor
Jauk, I.; Lorenzo Trueba, J.; Yamagishi, J.; Bonafonte, A.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
19th Annual Conference of the International Speech Communication
Any de l'edició
2018
Data de presentació
2018-09-01
Llibre d'actes
Interspeech 2018: 2-6 September 2018, Hyderabad
Pàgina inicial
3062
Pàgina final
3066
DOI
https://doi.org/10.21437/Interspeech.2018-2467 Obrir en finestra nova
Repositori
http://hdl.handle.net/2117/123860 Obrir en finestra nova
URL
https://www.isca-speech.org/archive/Interspeech_2018/pdfs/2467.pdf Obrir en finestra nova
Resum
In this paper we present a DNN based speech synthesis system trained on an audiobook including sentiment features predicted by the Stanford sentiment parser. The baseline system uses DNN to predict acoustic parameters based on conventional linguistic features, as they have been used in statistical parametric speech synthesis. The predicted parameters are transformed into speech using a conventional high-quality vocoder. In this paper, the conventional linguistic features are enriched using senti...
Paraules clau
Acoustic parameters, Baseline systems, DNN, Expressive speech synthesis, Linguistic features, Preliminary analysis, Sentiment analysis, Sentiment features, Speech communication, Speech synthesis, Speech synthesis system, Statistical parametric speech synthesis, TTS Linguistics
Grup de recerca
IDEAI-UPC Intelligent Data Science and Artificial Intelligence
TALP - Centre de Tecnologies i Aplicacions del Llenguatge i la Parla
VEU - Grup de Tractament de la Parla

Participants