| 1 |
Evaluation of Tacotron Based Synthesizers for Spanish and Basque
|
|
|
|
In: Applied Sciences; Volume 12; Issue 3; Pages: 1686 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
CCG Supertagging as Top-down Tree Generation
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2021)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Vowel Harmony Viewed as Error-Correcting Code
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2021)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Generating Adversarial Examples for Topic-dependent Argument Classification
|
|
|
|
In: COMMA 2020 - 8th International Conference on Computational Models of Argument ; https://hal.archives-ouvertes.fr/hal-02933266 ; COMMA 2020 - 8th International Conference on Computational Models of Argument, Sep 2020, Perugia, Italy (2020)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Automatic word count estimation from daylong child-centered recordings in various language environments using language-independent syllabification of speech
|
|
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Complexity of Stability
|
|
|
|
In: Leibniz International Proceedings in Informatics, 181 ; 31st International Symposium on Algorithms and Computation (ISAAC 2020) (2020)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
NAT: Noise-Aware Training for Robust Neural Sequence Labeling
|
|
|
|
In: Fraunhofer IAIS (2020)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
VoiceHome-2, an extended corpus for multichannel speech processing in real homes
|
|
|
|
In: ISSN: 0167-6393 ; EISSN: 1872-7182 ; Speech Communication ; https://hal.inria.fr/hal-01923108 ; Speech Communication, Elsevier : North-Holland, 2019, 106, pp.68-78. ⟨10.1016/j.specom.2018.11.002⟩ (2019)
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Towards Interpretability and Robustness of Machine Learning Models
|
|
Chen, Jianbo. - : eScholarship, University of California, 2019
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Assessing the Robustness of Conversational Agents using Paraphrases
|
|
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Robust speech recognition for german and dialectal broadcast programmes
|
|
|
|
In: Fraunhofer IAIS (2018)
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition
|
|
|
|
BASE
|
|
Show details
|
|
|
| 15 |
Lightweight Spoken Utterance Classification with CFG, tf-idf and Dynamic Programming
|
|
|
|
In: ISBN: 978-3-319-68455-0 ; Statistical Language and Speech Processing (SLSP) pp. 143-154 (2017)
|
|
BASE
|
|
Show details
|
|
|
| 16 |
A French corpus for distant-microphone speech processing in real homes
|
|
|
|
In: Interspeech 2016 ; https://hal.inria.fr/hal-01343060 ; Interspeech 2016, Sep 2016, San Francisco, United States (2016)
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Reconnaissance automatique de gestes manuels en langue des signes
|
|
|
|
In: RFIA 2016 ; RFIA'16: Le vingtième congrès national sur la Reconnaissance des Formes et l'Intelligence Artificielle ; https://hal.archives-ouvertes.fr/hal-01332141 ; RFIA'16: Le vingtième congrès national sur la Reconnaissance des Formes et l'Intelligence Artificielle , Jun 2016, Clermont-Ferrand, France (2016)
|
|
Abstract:
National audience ; Nous abordons dans ce papier la reconnaissance automa-tique de gestes manuels statiques pour des applications en langue des signes. Dans un travail précédent, nous avons proposé une méthode de reconnaissance de formes (classification et recherche) basée sur le recalage et les géodé-siques de formes. Cette méthode est conçue pour être ro-buste aux points aberrants et aux variabilités interindivi-duelles. Cette robustesse peut parfois mener à des confusions lorsque nous travaillons avec des classes de formes à faible dissemblance et donc à faible séparabilité. La diffé-rence entre ces classes de formes serait considérée comme donnée aberrante. Dans cet article, nous révisons notre méthode de reconnaissance de formes pour bien s'adap-ter aux classes à faible dissemblance. Nous nous plaçons en particulier dans le contexte de la reconnaissance de gestes manuels. Les résultats expérimentaux sur la base de référence GESTURES montrent tout l'intérêt de notre approche. Mots Clefs Langue de signes, reconnaissance de formes, recalage, ro-bustesse. Abstract This paper deals with the static hand gesture recognition for sign language applications. In a previous work, we proposed a method of pattern recognition (classification and research) based on robust registration and shapes geode-sics. This robustness may lead sometimes to errors when dealing with databases with low variability among shape classes so low separability. The difference between these classes could be interpreted as aberrant data. In this paper , we revise and adjust our method to be adapted for classes with low dissimilarity. We consider particularly the problem of gesture recognition. Experimental results on the GESTURES test base show the advantage of our approach.
|
|
Keyword:
[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing; robustness; shape recognition; Sign language; signal registration
|
|
URL: https://hal.archives-ouvertes.fr/hal-01332141
https://hal.archives-ouvertes.fr/hal-01332141/file/P01.pdf
https://hal.archives-ouvertes.fr/hal-01332141/document
|
|
BASE
|
|
Hide details
|
|
|
| 18 |
Investigation of Back-off Based Interpolation Between Recurrent Neural Network and N-gram Language Models (Author's Manuscript)
|
|
|
|
BASE
|
|
Show details
|
|
|
| 19 |
Lexicographic α-robustness: an application to the 1-median problem
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
