1 |
Automatic assessment of oral readings of young pupils
|
|
|
|
In: ISSN: 0167-6393 ; EISSN: 1872-7182 ; Speech Communication ; https://hal.archives-ouvertes.fr/hal-03585934 ; Speech Communication, Elsevier : North-Holland, 2022, 138, pp.67-79. ⟨10.1016/j.specom.2022.01.008⟩ ; https://www.sciencedirect.com/science/article/pii/S0167639322000164?via%3Dihub (2022)
|
|
BASE
|
|
Show details
|
|
2 |
Évaluation de dispositifs numériques innovants pour l’apprentissage de la lecture et de l’anglais : une expérimentation longitudinale en condition écologique
|
|
|
|
In: SFERE 2021 - 2ème édition du Colloque de SFERE-Provence ; https://hal.univ-grenoble-alpes.fr/hal-03187570 ; SFERE 2021 - 2ème édition du Colloque de SFERE-Provence, Mar 2021, Marseille, France (2021)
|
|
BASE
|
|
Show details
|
|
3 |
FLUENCE : projet de conception et d’expérimentation in-situ, longitudinale et à grande échelle d’applications tablettes pour prévenir les difficultés d’apprentissage de la lecture
|
|
|
|
In: SILE 2021 ; https://hal.univ-grenoble-alpes.fr/hal-03248965 ; SILE 2021, May 2021, Sherbrooke, Canada (2021)
|
|
BASE
|
|
Show details
|
|
4 |
Impact of Segmentation and Annotation in French end-to-end Synthesis
|
|
|
|
In: Proc. 11th ISCA Speech Synthesis Workshop (SSW 11) ; SSW 11th ISCA Speech Synthesis Workshop ; https://hal.archives-ouvertes.fr/hal-03362000 ; SSW 11th ISCA Speech Synthesis Workshop, Aug 2021, Budapest, Hungary. pp.13-18, ⟨10.21437/SSW.2021-3⟩ ; https://ssw11.hte.hu/ (2021)
|
|
Abstract:
International audience ; Audio books are commonly used to train text-to-speech models (TTS), as they offer large phonetic content with rather expressive pronunciation, but number and sizes of publicly available audio books corpora differ between languages. Moreover, the quality and accuracy of the available utterance segmentations are debatable. Yet, the impact of segmentation on the output synthesis is not well established. Additionally, utterances are generally used individually, without taking advantage of text level structuring information, even though they influence speaker reading. In this paper, we conduct a multidimensional evaluation of Tacotron2 trained on different segmentations and text level annotations of the same French corpus. We show that both spectrum accuracy and expressiveness depend on the segmentation used. In particular, a shorter segmentation, in addition with the annotation of paragraphs, benefits to spectrum reconstruction at the detriment of phrasing. Multidimensional analysis of mean opinion scores obtained with a MUSHRA-experiment revealed that phrasing was relatively more important than spectrum accuracy in perceptual judgement. This work serves as evidence that particular attention must be given to models evaluation, as well as how to use the training corpus to maximize synthesis characteristics of interest.
|
|
Keyword:
[INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]; [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing; [INFO]Computer Science [cs]; French dataset; French TTS; mixed-inputs TTS; Speech Synthesis
|
|
URL: https://doi.org/10.21437/SSW.2021-3 https://hal.archives-ouvertes.fr/hal-03362000/file/lenglet21_ssw.pdf https://hal.archives-ouvertes.fr/hal-03362000 https://hal.archives-ouvertes.fr/hal-03362000/document
|
|
BASE
|
|
Hide details
|
|
5 |
Ressources for End-to-End French Text-to-Speech Blizzard challenge ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Ressources for End-to-End French Text-to-Speech Blizzard challenge ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Predicting Multidimensional Subjective Ratings of Children' Readings from the Speech Signals for the Automatic Assessment of Fluency
|
|
|
|
In: LREC 2020 - 12th Conference on Language Resources and Evaluation (LREC 2020) ; https://hal.archives-ouvertes.fr/hal-03039160 ; LREC 2020 - 12th Conference on Language Resources and Evaluation (LREC 2020), May 2020, Marseille, France. pp.317-322 ; https://lrec2020.lrec-conf.org/en/ (2020)
|
|
BASE
|
|
Show details
|
|
9 |
Audio-visual synchronization in reading while listening to texts: Effects on visual behavior and verbal learning
|
|
|
|
In: ISSN: 0885-2308 ; EISSN: 1095-8363 ; Computer Speech and Language ; https://hal.archives-ouvertes.fr/hal-01575227 ; Computer Speech and Language, Elsevier, 2018, 47 (january), pp.79-92. ⟨10.1016/j.csl.2017.07.003⟩ (2018)
|
|
BASE
|
|
Show details
|
|
11 |
Embedding Context-Dependent Variations of Prosodic Contours using Variational Encoding for Decomposing the Structure of Speech Prosody ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Embedding Context-Dependent Variations of Prosodic Contours using Variational Encoding for Decomposing the Structure of Speech Prosody ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
A Weighted Superposition of Functional Contours Model for Modelling Contextual Prominence of Elementary Prosodic Contours ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
A Variational Prosody Model for Mapping the Context-Sensitive Variation of Functional Prosodic Prototypes ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
The significance of scope in modelling tones in Chinese ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
The significance of scope in modelling tones in Chinese ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Introduction to the special issue on auditory-visual expressive speech and gesture in humans and machines
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Using Karaoke to enhance reading while listening: impact on word memorization and eye movements
|
|
|
|
In: Speech and Language Technology for Education (SLaTE) ; SLaTE 2015 - ISCA Workshop on Speech and Language Technology in Education ; https://hal.archives-ouvertes.fr/hal-01192870 ; SLaTE 2015 - ISCA Workshop on Speech and Language Technology in Education, Sep 2015, Leipzig, Germany. pp.59-64 (2015)
|
|
BASE
|
|
Show details
|
|
20 |
Beyond Basic Emotions: Expressive Virtual Actors with Social Attitudes
|
|
|
|
In: 7th International ACM SIGGRAPH Conference on Motion in Games 2014 (MIG 2014) ; https://hal.archives-ouvertes.fr/hal-01064989 ; 7th International ACM SIGGRAPH Conference on Motion in Games 2014 (MIG 2014), Nov 2014, Los Angeles, United States. pp.39-47, ⟨10.1145/2668084.2668084⟩ (2014)
|
|
BASE
|
|
Show details
|
|
|
|