Mixed source model and its adapted vocal tract filter estimate for voice transformation and synthesis

Autor: Degottex, Gilles, Lanchantin, Pierre, Roebel, Axel, Rodet, Xavier

Publikováno v: In Speech Communication February 2013 55(2):278-294

Unsupervised segmentation of triplet Markov chains hidden with long-memory noise

Autor: Lanchantin, Pierre, Lapuyade-Lahorgue, Jérôme, Pieczynski, Wojciech

Publikováno v: In Signal Processing 2008 88(5):1134-1151

Making Sense of Variations: Introducing Alternatives in Speech Synthesis

Autor: Obin, Nicolas, Veaux, Christophe, Lanchantin, Pierre

Publikováno v: Veaux, C, Obin, N & Lanchantin, P 2012, Making Sense of Variations: Introducing Alternatives in Speech Synthesis . in Proceedings of the 6th International Conference on Speech Prosody 2012 . Speech Prosody, 6th International Conference, Shanghai, China, 22/05/12 . < http://sprosig.isle.illinois.edu/sp2012/uploadfiles/file/sp2012_submission_229.pdf >
Speech Prosody
Speech Prosody, May 2012, Shanghai, China

International audience; This paper addresses the use of speech alternatives to enrich speech synthesis systems. Speech alternatives denote the variety of strategies that a speaker can use to pronounce a sentence - depending on pragmatic constraints,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::afe7778fa54993be61f3a8f2a1b300e4
https://hal.archives-ouvertes.fr/hal-00663837

Discrete/Continuous Modelling of Speaking Style in HMM-based Speech Synthesis: Design and Evaluation

Autor: Obin, Nicolas, Lanchantin, Pierre, Lacheret, Anne, Rodet, Xavier

Publikováno v: Interspeech
Interspeech, Aug 2011, Florence, Italy

International audience; This paper assesses the ability of a HMM-based speech synthesis systems to model the speech characteristics of various speaking styles. A discrete/continuous HMM is presented to model the symbolic and acoustic speech character

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5b7cac6b651e8bb861369e08494359f1
https://hal.archives-ouvertes.fr/hal-00597780/document

Towards Improved HMM-based Speech Synthesis Using High-Level Syntactical Features

Autor: Obin, Nicolas, Lanchantin, Pierre, Avanzi, Mathieu, Lacheret, Anne, Rodet, Xavier

Publikováno v: Speech Prosody
Speech Prosody, 2010, Chicago, United States. pp.2000-2004

International audience; A major drawback of current Hidden Markov Model (HMM)-based speech synthesis is the monotony of the generated speech which is closely related to the monotony of the generated prosody. Complementary to model-oriented approaches

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::94a75c1a540129a052de4dbde5dc010f
https://hal.archives-ouvertes.fr/hal-00589083