Page: 1 2 3 4 5 6 7 8... 243
61 |
Does infant-directed speech help phonetic learning? A machine learning investigation
|
|
|
|
In: ISSN: 0364-0213 ; EISSN: 1551-6709 ; Cognitive Science ; https://hal.archives-ouvertes.fr/hal-03080098 ; Cognitive Science, Wiley, 2021, 45 (5), ⟨10.1111/cogs.12946⟩ (2021)
|
|
BASE
|
|
Show details
|
|
62 |
The Impact of Alcohol on L1 versus L2
|
|
|
|
In: ISSN: 0023-8309 ; Language and Speech ; https://hal.archives-ouvertes.fr/hal-03476236 ; Language and Speech, SAGE Publications (UK and US), 2021, 64 (3), pp.681-692. ⟨10.1177/0023830920953169⟩ (2021)
|
|
BASE
|
|
Show details
|
|
63 |
Management support system and group planning in continuing education ; Système d’aide à la gestion et planification de groupe en formation continue
|
|
|
|
In: https://hal.archives-ouvertes.fr/tel-03557025 ; Environnements Informatiques pour l'Apprentissage Humain. Université de Lille, CRIStAL UMR 9189, 2021. Français (2021)
|
|
BASE
|
|
Show details
|
|
64 |
Extraction of Narrative Structure from TV Series ; Extraction de la structure narrative de séries TV
|
|
|
|
In: https://halshs.archives-ouvertes.fr/tel-03474054 ; Linguistics. Université Paris-Saclay/Université Paris-Sud; LISN; CNRS, 2021. English (2021)
|
|
BASE
|
|
Show details
|
|
65 |
Evolution and differentiation of the cybersecurity communities in three social question and answer sites: A mixed-methods analysis.
|
|
|
|
In: PloS one, vol 16, iss 12 (2021)
|
|
BASE
|
|
Show details
|
|
66 |
A Hierarchical Computational Framework for Social Interaction Understanding: Interactiveness, Shared Attention, Gaze Communication and Triadic Belief Dynamics
|
|
Fan, Lifeng. - : eScholarship, University of California, 2021
|
|
BASE
|
|
Show details
|
|
67 |
Mapping International Geopolitical Agenda. Continuing National Conceptions of the Emerging European Crisis
|
|
|
|
In: ISSN: 2624-909X ; EISSN: 2624-909X ; Frontiers in Big Data ; https://halshs.archives-ouvertes.fr/halshs-03506950 ; Frontiers in Big Data, Frontiers, 2021, 4, ⟨10.3389/fdata.2021.718809⟩ (2021)
|
|
BASE
|
|
Show details
|
|
68 |
D-Cliques: Compensating for Data Heterogeneity with Topology in Decentralized Federated Learning
|
|
|
|
In: https://hal.inria.fr/hal-03498160 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
69 |
Machine Learning of Motion Statistics Reveals the Kinematic Signature of the Identity of a Person in Sign Language
|
|
|
|
In: ISSN: 2296-4185 ; Frontiers in Bioengineering and Biotechnology ; https://hal.archives-ouvertes.fr/hal-03298752 ; Frontiers in Bioengineering and Biotechnology, Frontiers, 2021, 9, ⟨10.3389/fbioe.2021.710132⟩ (2021)
|
|
BASE
|
|
Show details
|
|
70 |
Some contributions to computational Bayesian methods with application to phylolinguistics ; Quelques contributions aux méthodes computationnelles bayesiennes, avec applications à la phylolinguistique
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-03546821 ; Statistics [math.ST]. Université Paris sciences et lettres, 2021. English. ⟨NNT : 2021UPSLD008⟩ (2021)
|
|
BASE
|
|
Show details
|
|
71 |
A review of data collection practices using electromagnetic articulography
|
|
|
|
In: ISSN: 1868-6354 ; Laboratory Phonology : Journal of the Association for Laboratory Phonology ; https://hal.archives-ouvertes.fr/hal-03476230 ; Laboratory Phonology : Journal of the Association for Laboratory Phonology, De Gruyter, 2021, 12 (1), pp.6. ⟨10.5334/labphon.237⟩ (2021)
|
|
BASE
|
|
Show details
|
|
72 |
Deux méthodes d’extraction automatique des connaissances pour essayer de comprendre la structuration de la conscience phonologique chez l’enfant
|
|
|
|
In: 18e Rencontres du Réseau Français de Phonologie ; https://hal.archives-ouvertes.fr/hal-03162037 ; 18e Rencontres du Réseau Français de Phonologie, Jul 2021, Clermont-Ferrand, France (2021)
|
|
BASE
|
|
Show details
|
|
73 |
Multimodal Coarticulation Modeling : Towards the animation of an intelligible talking head ; Modélisation de la coarticulation multimodale : vers l'animation d'une tête parlante intelligible
|
|
|
|
In: https://hal.univ-lorraine.fr/tel-03203815 ; Intelligence artificielle [cs.AI]. Université de Lorraine, 2021. Français. ⟨NNT : 2021LORR0019⟩ (2021)
|
|
BASE
|
|
Show details
|
|
74 |
Modelling repeated paired phonetic measures using linear mixed models with correlated errors
|
|
|
|
In: ISSN: 2152-372X ; Case Studies in Business, Industry and Government Statistics ; https://hal.archives-ouvertes.fr/hal-03235741 ; Case Studies in Business, Industry and Government Statistics, Société Française de Statistique, 2021, 8, pp.28-46 ; http://csbigs.fr/article/view/811 (2021)
|
|
BASE
|
|
Show details
|
|
75 |
A logistic regression model for predicting child language performance ; Un modèle de régression logistique pour la prédiction du développement langagier chez l'enfant
|
|
|
|
In: SIS 2021, 50th Annuale Conference of the Italian Statistical Society" ; https://hal.archives-ouvertes.fr/hal-03318721 ; SIS 2021, 50th Annuale Conference of the Italian Statistical Society", Jun 2021, Pise, Italy (2021)
|
|
BASE
|
|
Show details
|
|
76 |
L'art des controverses ; L'art des controverses: La création pour apprendre
|
|
|
|
In: Controverses mode d'emploi ; https://hal.telecom-paris.fr/hal-03140312 ; Presses de la fondation nationale des sciences politiques. Controverses mode d'emploi, pp.307-309, 2021 (2021)
|
|
BASE
|
|
Show details
|
|
77 |
The Machine in the Garden of Meter and Rythm
|
|
|
|
In: Plotting Poetry. On Mechanically-Enhanced Reading ; https://hal.telecom-paris.fr/hal-03255491 ; Bories, Anne-Sophie ; Purnelle, Gérald ; Marchal, Hugues. Plotting Poetry. On Mechanically-Enhanced Reading, Presses universitaires de Liège, 2021, 978-2-87562-280-8 (2021)
|
|
BASE
|
|
Show details
|
|
78 |
Presence, flow, and narrative absorption questionnaires: a scoping review
|
|
|
|
In: Open Research Europe ; https://hal.archives-ouvertes.fr/hal-03228676 ; Open Research Europe, 2021, 1, pp.11. ⟨10.12688/openreseurope.13277.1⟩ (2021)
|
|
BASE
|
|
Show details
|
|
79 |
Learning a weather dictionary of atmospheric patterns using Latent Dirichlet Allocation
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03258523 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
80 |
Learning emotions latent representation with CVAE for Text-Driven Expressive AudioVisual Speech Synthesis
|
|
|
|
In: ISSN: 0893-6080 ; Neural Networks ; https://hal.inria.fr/hal-03204193 ; Neural Networks, Elsevier, 2021, 141, pp.315-329. ⟨10.1016/j.neunet.2021.04.021⟩ (2021)
|
|
Abstract:
International audience ; Great improvement has been made in the field of expressive audiovisual Text-to-Speech synthesis (EAVTTS) thanks to deep learning techniques. However, generating realistic speech is still an open issue and researchers in this area have been focusing lately on controlling the speech variability.In this paper, we use different neural architectures to synthesize emotional speech. We study the application of unsupervised learning techniques for emotional speech modeling as well as methods for restructuring emotions representation to make it continuous and more flexible. This manipulation of the emotional representation should allow us to generate new styles of speech by mixing emotions. We first present our expressive audiovisual corpus. We validate the emotional content of this corpus with three perceptual experiments using acoustic only, visual only and audiovisual stimuli.After that, we analyze the performance of a fully connected neural network in learning characteristics specific to different emotions for the phone duration aspect and the acoustic and visual modalities.We also study the contribution of a joint and separate training of the acoustic and visual modalities in the quality of the generated synthetic speech.In the second part of this paper, we use a conditional variational auto-encoder (CVAE) architecture to learn a latent representation of emotions. We applied this method in an unsupervised manner to generate features of expressive speech. We used a probabilistic metric to compute the overlapping degree between emotions latent clusters to choose the best parameters for the CVAE. By manipulating the latent vectors, we were able to generate nuances of a given emotion and to generate new emotions that do not exist in our database. For these new emotions, we obtain a coherent articulation. We conducted four perceptual experiments to evaluate our findings.
|
|
Keyword:
[MATH.MATH-MG]Mathematics [math]/Metric Geometry [math.MG]; [SCCO.COMP]Cognitive science/Computer science; [SCCO.LING]Cognitive science/Linguistics; [SDV.OT]Life Sciences [q-bio]/Other [q-bio.OT]; [SHS.INFO]Humanities and Social Sciences/Library and information sciences; [SHS.LANGUE]Humanities and Social Sciences/Linguistics; [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing; [STAT.ML]Statistics [stat]/Machine Learning [stat.ML]; bidirectional long short-term memory (BLSTM); conditional variationalauto-encoder; deeplearning; emotion; Expressive audiovisual speech synthesis; Expressive talking avatar; facial expression
|
|
URL: https://doi.org/10.1016/j.neunet.2021.04.021 https://hal.inria.fr/hal-03204193/document https://hal.inria.fr/hal-03204193 https://hal.inria.fr/hal-03204193/file/neural_networks_journal-8.pdf
|
|
BASE
|
|
Hide details
|
|
Page: 1 2 3 4 5 6 7 8... 243
|
|