1 |
Neural-Driven Search-Based Paraphrase Generation
|
|
|
|
In: 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021) ; https://hal.archives-ouvertes.fr/hal-03540926 ; 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021), Apr 2021, Kiev, Ukraine (2021)
|
|
BASE
|
|
Show details
|
|
2 |
Corpus design for expressive speech: impact of the utterance length
|
|
|
|
In: 10th International Conference on Speech Prosody 2020 ; https://hal.archives-ouvertes.fr/hal-02874005 ; 10th International Conference on Speech Prosody 2020, May 2020, Tokyo, Japan. pp.955-959, ⟨10.21437/SpeechProsody.2020-195⟩ (2020)
|
|
BASE
|
|
Show details
|
|
3 |
Can we Generate Emotional Pronunciations for Expressive Speech Synthesis?
|
|
|
|
In: ISSN: 1949-3045 ; IEEE Transactions on Affective Computing ; https://hal.archives-ouvertes.fr/hal-01802463 ; IEEE Transactions on Affective Computing, Institute of Electrical and Electronics Engineers, 2020, 11 (4), pp.684-695. ⟨10.1109/TAFFC.2018.2828429⟩ (2020)
|
|
Abstract:
International audience ; 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. However, prosody is highly related to the sequence of phonemes to be expressed. This article raises two issues in the generation of emotional pronunciations for TTS systems. The first issue consists in designing an automatic pronunciation generation method from text, while the second issue addresses the very existence of emotional pronunciations through experiments conducted on emotional speech. To do so, an innovative pronunciation adaptation method which automatically adapts canonical phonemes first to those labeled in the corpus used to create a synthetic voice, then to those labeled in an expressive corpus, is presented. This method consists in training conditional random fields pronunciation models with prosodic, linguistic, phonological and articulatory features. The analysis of emotional pronunciations reveals strong dependencies between prosody and phoneme assimilation or elisions. According to perception tests, the double adaptation allows to synthesize expressive speech samples of good quality, but emotion-specific pronunciations are too subtle to be perceived by testers.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; conditional random fields; emotion; Expressive speech synthesis; pronunciation adaptation
|
|
URL: https://hal.archives-ouvertes.fr/hal-01802463 https://hal.archives-ouvertes.fr/hal-01802463/document https://hal.archives-ouvertes.fr/hal-01802463/file/TAC2017.pdf https://doi.org/10.1109/TAFFC.2018.2828429
|
|
BASE
|
|
Hide details
|
|
4 |
Style versus Content: A distinction without a (learnable) difference?
|
|
|
|
In: International Conference on Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-03112354 ; International Conference on Computational Linguistics, Dec 2020, Virtual, Spain (2020)
|
|
BASE
|
|
Show details
|
|
5 |
Introducing Prosodic Speaker Identity for a Better Expressive Speech Synthesis Control
|
|
|
|
In: 10th International Conference on Speech Prosody 2020 ; https://hal.archives-ouvertes.fr/hal-03000148 ; 10th International Conference on Speech Prosody 2020, May 2020, Tokyo, Japan. pp.935-939, ⟨10.21437/speechprosody.2020-191⟩ (2020)
|
|
BASE
|
|
Show details
|
|
7 |
SynPaFlex-Corpus: An Expressive French Audiobooks Corpus Dedicated to Expressive Speech Synthesis
|
|
|
|
In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) ; https://hal.archives-ouvertes.fr/hal-01826690 ; Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), May 2018, Miyazaki, Japan ; http://lrec2018.lrec-conf.org/en/ (2018)
|
|
BASE
|
|
Show details
|
|
8 |
Discourse phrases classification: direct vs. narrative audio speech
|
|
|
|
In: Speech Prosody ; https://hal.archives-ouvertes.fr/hal-01790910 ; Speech Prosody, Jun 2018, Poznan, Poland (2018)
|
|
BASE
|
|
Show details
|
|
9 |
Disfluency Insertion for Spontaneous TTS: Formalization and Proof of Concept
|
|
|
|
In: SLSP 2018 - 6th International Conference on Statistical Language and Speech Processing ; https://hal.inria.fr/hal-01840798 ; SLSP 2018 - 6th International Conference on Statistical Language and Speech Processing, Oct 2018, Mons, Belgium. pp.1-12, ⟨10.1007/978-3-030-00810-9_4⟩ (2018)
|
|
BASE
|
|
Show details
|
|
10 |
Big Five vs. Prosodic Features as Cues to Detect Abnormality in SSPNET-Personality Corpus
|
|
|
|
In: Interspeech ; https://hal.inria.fr/hal-01583510 ; Interspeech, Aug 2017, Stockholm, Sweden ; http://www.interspeech2017.org/ (2017)
|
|
BASE
|
|
Show details
|
|
11 |
First Experiments to Detect Anomaly Using Personality Traits vs. Prosodic Features
|
|
|
|
In: 19th International Conference on Speech and Computer (SPECOM) ; https://hal.inria.fr/hal-01583539 ; 19th International Conference on Speech and Computer (SPECOM), Sep 2017, Hatfield, Hertfordshire, United Kingdom ; https://link.springer.com/chapter/10.1007/978-3-319-66429-3_37 (2017)
|
|
BASE
|
|
Show details
|
|
12 |
The IRISA Text-To-Speech System for the Blizzard Challenge 2017
|
|
|
|
In: Blizzard Challenge ; https://hal.inria.fr/hal-01662361 ; Blizzard Challenge, Aug 2017, Stockholm, Sweden (2017)
|
|
BASE
|
|
Show details
|
|
13 |
Perception of expressivity in TTS: linguistics, phonetics or prosody?
|
|
|
|
In: Statistical Language and Speech Processing ; https://hal-univ-lemans.archives-ouvertes.fr/hal-01623916 ; Statistical Language and Speech Processing, Oct 2017, Le Mans, France. pp.262-274, ⟨10.1007/978-3-319-68456-7_22⟩ ; http://grammars.grlmc.com/SLSP2017/index.php (2017)
|
|
BASE
|
|
Show details
|
|
14 |
Statistical Pronunciation Adaptation for Spontaneous Speech Synthesis
|
|
|
|
In: Text, Speech and Dialogue (TSD) ; https://hal.inria.fr/hal-01532035 ; Text, Speech and Dialogue (TSD), Aug 2017, Prague, Czech Republic (2017)
|
|
BASE
|
|
Show details
|
|
15 |
De l'utilisation de descripteurs issus de la linguistique computationnelle dans le cadre de la synthèse par HMM
|
|
|
|
In: Journées d'Études sur la Parole ; https://hal.inria.fr/hal-01338953 ; Journées d'Études sur la Parole, Jul 2016, Paris, France (2016)
|
|
BASE
|
|
Show details
|
|
16 |
Patrons Rythmiques et Genres Littéraires en Synthèse de la Parole
|
|
|
|
In: Journées d'Études sur la Parole ; https://hal.inria.fr/hal-01338959 ; Journées d'Études sur la Parole, Jul 2016, Paris, France (2016)
|
|
BASE
|
|
Show details
|
|
17 |
Adaptation de la prononciation pour la synthèse de la parole spontanée en utilisant des informations linguistiques
|
|
|
|
In: Journées d'Études sur la Parole ; https://hal.inria.fr/hal-01321361 ; Journées d'Études sur la Parole, Jul 2016, Paris, France (2016)
|
|
BASE
|
|
Show details
|
|
18 |
Rhythmic Patterns and Literary Genres in Synthesized Speech
|
|
|
|
In: Speech Prosody ; https://hal.inria.fr/hal-01338873 ; Speech Prosody, 2016, Boston, United States (2016)
|
|
BASE
|
|
Show details
|
|
19 |
Une pénalité floue fondée phonologiquement pour améliorer la Sélection d'Unité
|
|
|
|
In: Journées d'Études sur la Parole ; https://hal.inria.fr/hal-01338948 ; Journées d'Études sur la Parole, Jul 2016, Paris, France (2016)
|
|
BASE
|
|
Show details
|
|
20 |
The IRISA Text-To-Speech System for the Blizzard Challenge 2016
|
|
|
|
In: Blizzard Challenge 2016 workshop ; https://hal.inria.fr/hal-01375897 ; Blizzard Challenge 2016 workshop, Sep 2016, Cupertino, United States (2016)
|
|
BASE
|
|
Show details
|
|
|
|