{"id":87,"date":"2016-01-27T14:14:42","date_gmt":"2016-01-27T13:14:42","guid":{"rendered":"https:\/\/synpaflex.irisa.fr\/?page_id=87"},"modified":"2020-05-26T10:06:00","modified_gmt":"2020-05-26T08:06:00","slug":"publications","status":"publish","type":"page","link":"http:\/\/synpaflex.irisa.fr\/fr\/publications\/","title":{"rendered":"Publications"},"content":{"rendered":"<p><strong>Revues Internationales<\/strong><\/p>\n<ul>\n<li>Tahon Marie Lecorv\u00e9 Gw\u00e9nol\u00e9 and Lolive Damien. <b>Can we Generate Emotional Pronunciations for Expressive Speech Synthesis?<\/b>, In <i>IEEE Transactions on Affective Computing<\/i>, 2018.<\/li>\n<\/ul>\n<p><strong>Conf\u00e9rences Internationales\u00a0<\/strong><\/p>\n<ul>\n<li>Elisabeth Delais-Roussarie,\u00a0Damien Lolive, Hiyon Yoo and David Guennec.\u00a0<b>Rhythmic Patterns and Literary Genres in Synthesized Speech<\/b>, In\u00a0<i>Speech Prosody 2016<\/i>, 2016.<\/li>\n<li>Katarina Bartkova, Denis Jouvet, Elisabeth Delais-Roussarie.\u00a0<strong>Prosodic Parameters and Prosodic Structures of French Emotional Data<\/strong>,\u00a0In\u00a0<i>Speech Prosody 2016<\/i>, 2016.<\/li>\n<li>Marie Tahon, Raheel Qader, Gw\u00e9nol\u00e9 Lecorv\u00e9 and\u00a0Damien Lolive.\u00a0<b>Improving TTS with corpus-specific pronunciation adaptation<\/b>, In\u00a0<i>Proceedings of the International Conference on Speech Communication and Technology (Interspeech)<\/i>, 2016.<\/li>\n<li>Marie Tahon, Raheel Qader, Gw\u00e9nol\u00e9 Lecorv\u00e9 and\u00a0Damien Lolive.\u00a0<b>Optimal feature set and minimal training size for pronunciation adaptation in TTS\u00a0<\/b>, In\u00a0<i>Proceedings of the International Conference on Statistical Language and Speech Processing (SLSP)<\/i>, 2016.<\/li>\n<li>Pierre Alain, Jonathan Chevelu, David Guennec, Gw\u00e9nol\u00e9 Lecorv\u00e9 and Damien Lolive. <b>The IRISA Text-To-Speech System for the Blizzard Challenge 2016<\/b>. In <i>Blizzard Challenge 2016 Workshop<\/i>, Sep 2016, Cupertino, USA.<\/li>\n<li>Pierre Alain, Nelly Barbot, Jonathan Chevelu, Gw\u00e9nol\u00e9 Lecorv\u00e9, Damien Lolive, Claude Simon and Marie Tahon. <b>The IRISA Text-To-Speech System for the Blizzard Challenge 2017<\/b>. In <i>Blizzard Challenge 2017 Workshop<\/i>, Aug 2017, Stockholm, Sweden.<\/li>\n<li>Raheel Qader, Gw\u00e9nol\u00e9 Lecorv\u00e9, Damien Lolive, Marie Tahon, Pascale S\u00e9billot. <b>Statistical Pronunciation Adaptation for Spontaneous Speech Synthesis<\/b>. In Proc. of Text, Speech and Dialogue (TSD), Prague, Czech Republic, 2017.<\/li>\n<li>Marie Tahon, Gw\u00e9nol\u00e9 Lecorv\u00e9, Damien Lolive, Raheel Qader. <b>Perception of expressivity in TTS: linguistics, phonetics or prosody?<\/b>, In Proc. of the International Conference on Statistical Language and Speech Processing (SLSP), Le Mans, France, 2017.<\/li>\n<li>Aghilas Sini, Damien Lolive, Ga\u00eblle Vidal, Marie Tahon and \u00c9lisabeth Delais-Roussarie. <b>SynPaFlex-Corpus: An Expressive French Audiobooks Corpus Dedicated to Expressive Speech Synthesis<\/b>, In Proc. of LREC, Miyazaki, Japan, 2018.<\/li>\n<li>Marie Tahon and Damien Lolive. <b>Discourse phrases classification: direct vs. narrative audio speech<\/b>, In Proc. of Speech Prosody, Pozna\u0144, Poland, 2018.<\/li>\n<li>Pierre Alain, Gwe\u0301nole\u0301 Lecorve\u0301, Damien Lolive, Antoine Perquin.<br \/>\n<b>The IRISA Text-To-Speech System for the Blizzard Challenge 2018.<\/b> In Blizzard Challenge 2018 Workshop, Sep 2018, Hyderabad, India.<\/li>\n<li>Raheel Qader, Gw\u00e9nol\u00e9 Lecorv\u00e9, Damien Lolive and Pascale S\u00e9billot. <b>Disfluency Insertion for Spontaneous TTS: Formalization and Proof of Concept<\/b>, In Proc. of the International Conference on Statistical Language and Speech Processing (SLSP), Mons, Belgium, 2018.<\/li>\n<li>Antoine Perquin, Gw\u00e9nol\u00e9 Lecorv\u00e9, Damien Lolive and Laurent Amsaleg. <b>Phone-Level Embeddings for Unit Selection Speech Synthesis<\/b>, In Proc. of the International Conference on Statistical Language and Speech Processing (SLSP), Mons, Belgium, 2018.<\/li>\n<li>Meysam Shamsi, Damien Lolive, Nelly Barbot and Jonathan Chevelu.\u00a0<b>Corpus Design using Convolutional Auto-Encoder Embeddings for Audio-Book Synthesis<\/b>, In\u00a0<i>Proceedings of the International Conference on Speech Communication and Technology (Interspeech)<\/i>, 2019.<\/li>\n<li>Meysam Shamsi, Damien Lolive, Nelly Barbot and Jonathan Chevelu.\u00a0<b>Investigating the relation between voice corpus design and hybrid synthesis under reduction constraint<\/b>, In\u00a0<i>In Proc. of the International Conference on Statistical Language and Speech Processing (SLSP),<\/i> Ljubljana, Slovenia, 2019.<\/li>\n<li>Meysam Shamsi, Damien Lolive, Nelly Barbot and Jonathan Chevelu.\u00a0<b>Script Selection using Convolutional Auto-encoder for TTS Speech Corpus<\/b>, In\u00a0<i>Proc. of the international conference on speech and computer<\/i>, Istanbul, Turkey, 2019.<\/li>\n<li>Aghilas Sini, S\u00e9bastien Le Maguer, Damien Lolive and Elisabeth Delais-Roussarie.\u00a0<b>Introducing Prosodic Speaker Identity for a Better Expressive Speech Synthesis Control<\/b>, In\u00a0<i>Proc. of the international conference on speech prosody<\/i>, 2020.<\/li>\n<li>Meysam Shamsi, Jonathan Chevelu, Nelly Barbot and Damien Lolive.\u00a0<b>Corpus design for expressive speech: impact of the utterance length<\/b>, In\u00a0<i>Proc. of the international conference on speech prosody<\/i>, 2020.<\/li>\n<\/ul>\n<p><strong>Conf\u00e9rences Nationales\u00a0<\/strong><\/p>\n<ul>\n<li>Elisabeth Delais-Roussarie,\u00a0Damien Lolive, Hiyon Yoo and David Guennec.\u00a0<b>Patrons Rythmiques et Genres Litt\u00e9raires en Synth\u00e8se de la Parole<\/b>, In\u00a0<i>Actes de la conf\u00e9rence JEP 2016<\/i>, 2016.<\/li>\n<li>Aghilas Sini, Elisabeth Delais-Roussarie, Damien Lolive. <b>Annotation automatique des types de discours dans des livres audio en vue d\u2019une oralisation par un syst\u00e8me de synth\u00e8se<\/b>, In Actes des Traitement Automatique du Langage Naturel (TALN), Rennes, France, 2018.<\/li>\n<\/ul>\n<p><\/p>","protected":false},"excerpt":{"rendered":"<p>Revues Internationales Tahon Marie Lecorv\u00e9 Gw\u00e9nol\u00e9 and Lolive Damien. Can we Generate Emotional Pronunciations for Expressive Speech Synthesis?, In IEEE Transactions on Affective Computing, 2018. Conf\u00e9rences Internationales\u00a0 Elisabeth Delais-Roussarie,\u00a0Damien Lolive, Hiyon Yoo and David Guennec.\u00a0Rhythmic Patterns and Literary Genres in Synthesized Speech, In\u00a0Speech Prosody 2016, 2016. Katarina Bartkova, Denis Jouvet, Elisabeth Delais-Roussarie.\u00a0Prosodic Parameters and Prosodic &hellip; <\/p>\n<p><a class=\"more-link btn\" href=\"http:\/\/synpaflex.irisa.fr\/fr\/publications\/\">Lire la suite<\/a><\/p>\n","protected":false},"author":906,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-87","page","type-page","status-publish","hentry","nodate","item-wrap"],"_links":{"self":[{"href":"http:\/\/synpaflex.irisa.fr\/fr\/wp-json\/wp\/v2\/pages\/87","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/synpaflex.irisa.fr\/fr\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"http:\/\/synpaflex.irisa.fr\/fr\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"http:\/\/synpaflex.irisa.fr\/fr\/wp-json\/wp\/v2\/users\/906"}],"replies":[{"embeddable":true,"href":"http:\/\/synpaflex.irisa.fr\/fr\/wp-json\/wp\/v2\/comments?post=87"}],"version-history":[{"count":35,"href":"http:\/\/synpaflex.irisa.fr\/fr\/wp-json\/wp\/v2\/pages\/87\/revisions"}],"predecessor-version":[{"id":223,"href":"http:\/\/synpaflex.irisa.fr\/fr\/wp-json\/wp\/v2\/pages\/87\/revisions\/223"}],"wp:attachment":[{"href":"http:\/\/synpaflex.irisa.fr\/fr\/wp-json\/wp\/v2\/media?parent=87"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}