Phone-Level Embeddings for Unit Selection Speech Synthesis

Antoine Perquin 1 Gwénolé Lecorvé 1 Damien Lolive 1 Laurent Amsaleg 2
1 EXPRESSION - Expressiveness in Human Centered Data/Media
UBS - Université de Bretagne Sud, IRISA-D6 - MEDIA ET INTERACTIONS
2 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA_D6 - MEDIA ET INTERACTIONS
Abstract : Deep neural networks have become the state of the art in speech synthesis. They have been used to directly predict signal parameters or provide unsupervised speech segment descriptions through embeddings. In this paper, we present four models with two of them enabling us to extract phone-level embeddings for unit selection speech synthesis. Three of the models rely on a feed-forward DNN, the last one on an LSTM. The resulting embeddings enable replacing usual expert-based target costs by an euclidean distance in the embedding space. This work is conducted on a French corpus of an 11 hours audiobook. Perceptual tests show the produced speech is preferred over a unit selection method where the target cost is defined by an expert. They also show that the embeddings are general enough to be used for different speech styles without quality loss. Furthermore, objective measures and a perceptual test on statistical parametric speech synthesis show that our models perform comparably to state-of-the-art models for parametric signal generation, in spite of necessary simplifications, namely late time integration and information compression.
Document type :
Conference papers
Liste complète des métadonnées
https://hal.archives-ouvertes.fr/hal-01840812
Contributor : Antoine Perquin <>
Submitted on : Monday, July 16, 2018 - 5:05:05 PM
Last modification on : Thursday, February 7, 2019 - 4:53:15 PM
Document(s) archivé(s) le : Wednesday, October 17, 2018 - 4:24:54 PM

File

samplepaper.pdf
Files produced by the author(s)

Identifiers

Collections

INSTITUT-TELECOM | IRISA-INSA-R | UNIV-RENNES1 | CENTRALESUPELEC | IRISA | INSA-RENNES | INRIA | UNIV-RENNES | UR1-UFR-ISTIC | IRISA-D6

Citation

Antoine Perquin, Gwénolé Lecorvé, Damien Lolive, Laurent Amsaleg. Phone-Level Embeddings for Unit Selection Speech Synthesis. SLSP 2018 - 6th International Conference on Statistical Language and Speech Processing, Oct 2018, Mons, Belgium. pp.21-31, ⟨10.1007/978-3-030-00810-9_3⟩. ⟨hal-01840812⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

273

Files downloads

225

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD