Can we generate emotional pronunciations for expressive speech synthesis?

M Tahon, G Lecorvé, D Lolive - IEEE Transactions on Affective …, 2018 - ieeexplore.ieee.org
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 …

Speech recognition and text-to-speech learning system

P Zhao, K Yao, M Leung, B Yan - US Patent 10,089,974, 2018 - Google Patents
An example text-to-speech learning system performs a method for generating a
pronunciation sequence conversion model. The method includes generating a first …

Improving TTS with corpus-specific pronunciation adaptation

M Tahon, R Qader, G Lecorvé, D Lolive - Interspeech, 2016 - inria.hal.science
Text-to-speech (TTS) systems are built on speech corpora which are labeled with carefully
checked and segmented phonemes. However, phoneme sequences generated by …

Optimal feature set and minimal training size for pronunciation adaptation in TTS

M Tahon, R Qader, G Lecorvé, D Lolive - Statistical Language and Speech …, 2016 - Springer
Abstract Text-to-Speech (TTS) systems rely on a grapheme-to-phoneme converter which is
built to produce canonical, or statically stylized, pronunciations. Hence, the TTS quality …

Traitement automatique de la parole expressive: retour vers des systèmes interprétables?

M Tahon - 2023 - hal.science
La parole est un moyen de communication fondamental qui s' inscrit dans une interaction
entre le locuteur et ses auditeurs. En plus du contenu sémantique, le signal de parole nous …

Statistical pronunciation adaptation for spontaneous speech synthesis

R Qader, G Lecorvé, D Lolive, M Tahon… - Text, Speech, and …, 2017 - Springer
To bring more expressiveness into text-to-speech systems, this paper presents a new
pronunciation variant generation method which works by adapting standard, ie, dictionary …

[PDF][PDF] Traitement automatique du style dans le langage naturel: quelques contributions et perspectives

G Lecorvé - 2020 - hal.science
The study of natural language is present in multiple scientific disciplines. In linguistics, this
study is purpose itself and comes in many specific areas. In neuro-sciences also, language …

Adaptation de la prononciation pour la synthèse de la parole spontanée en utilisant des informations linguistiques (Pronunciation adaptation for spontaneous speech …

R Qader, G Lecorvé, D Lolive… - Actes de la conférence …, 2016 - aclanthology.org
Cet article présente une nouvelle méthode d'adaptation de la prononciation dont le but est
de reproduire le style spontané. Il s' agit d'une tâche-clé en synthèse de la parole car elle …

Training and testing the TDNN-OPGRU acoustic model on English read and spontaneous speech

GD Genkov - 2021 - repository.tudelft.nl
Automatic phoneme recognition (APR) is the process of recognizing phonemes (spoken
sounds) in a recording of speech. It can be used for any application requiring fast and …

Statistical Pronunciation Adaptation for Spontaneous Speech Synthesis

P Sébillot - Text, Speech, and Dialogue: 20th International …, 2017 - books.google.com
To bring more expressiveness into text-to-speech systems, this paper presents a new
pronunciation variant generation method which works by adapting standard, ie, dictionary …