1 |
Integrating a Phrase Structure Corpus Grammar and a Lexical-Semantic Network: the HOLINET Knowledge Graph
|
|
|
|
In: Proceedings of LREC 2022 ; https://hal-amu.archives-ouvertes.fr/hal-03655636 ; Proceedings of LREC 2022, Jun 2022, Marseille, France (2022)
|
|
BASE
|
|
Show details
|
|
2 |
Multistream neural architectures for cued-speech recognition using a pre-trained visual feature extractor and constrained CTC decoding
|
|
|
|
In: ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing ; https://hal.archives-ouvertes.fr/hal-03578503 ; ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapour, Singapore (2022)
|
|
BASE
|
|
Show details
|
|
3 |
What Do Cognitive Networks Do? Simulations of Spoken Word Recognition Using the Cognitive Network Science Approach
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Sequential and network analyses to describe multiple signal use in captive mangabeys
|
|
|
|
In: ISSN: 0003-3472 ; EISSN: 1095-8282 ; Animal Behaviour ; https://hal.archives-ouvertes.fr/hal-03480471 ; Animal Behaviour, Elsevier Masson, 2021, 182, pp.203-226. ⟨10.1016/j.anbehav.2021.09.005⟩ (2021)
|
|
BASE
|
|
Show details
|
|
5 |
Linking an Abstract Corpus Grammar to a Lexical Semantic Network
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03552630 ; [Research Report] Laboratoire Parole et Langage – Université d’Aix-Marseille. 2021 (2021)
|
|
BASE
|
|
Show details
|
|
6 |
Coupler syntaxe et sémantique dans une même base de connaissances linguistiques
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03552622 ; [Rapport de recherche] Laboratoire Parole et Langage – Université d’Aix-Marseille. 2021 (2021)
|
|
BASE
|
|
Show details
|
|
7 |
Database of word-level statistics for Mandarin Chinese (DoWLS-MAN)
|
|
|
|
In: ISSN: 1554-351X ; EISSN: 1554-3528 ; Behavior Research Methods ; https://hal.archives-ouvertes.fr/hal-03328510 ; Behavior Research Methods, Psychonomic Society, Inc, In press, ⟨10.3758/s13428-021-01620-7⟩ (2021)
|
|
BASE
|
|
Show details
|
|
8 |
What does the Canary Say? Low-Dimensional GAN Applied to Birdsong
|
|
|
|
In: https://hal.inria.fr/hal-03244723 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
9 |
Modeling the neural network responsible for song learning ; Modélisation du réseau neuronal responsable de l'apprentissage du chant chez l'oiseau chanteur
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-03217834 ; Modeling and Simulation. Université de Bordeaux, 2021. English. ⟨NNT : 2021BORD0107⟩ (2021)
|
|
BASE
|
|
Show details
|
|
10 |
Cortical basis of vocalization in behaving freely moving minipigs ; Bases corticales de la vocalisation chez le miniporc en comportement
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-03353386 ; Neuroscience. Université Grenoble Alpes [2020-.], 2021. English. ⟨NNT : 2021GRALS013⟩ (2021)
|
|
BASE
|
|
Show details
|
|
11 |
Automatic Classification of Phonation Types in Spontaneous Speech: Towards a New Workflow for the Characterization of Speakers’ Voice Quality
|
|
|
|
In: Interspeech 2021 ; https://hal.archives-ouvertes.fr/hal-03334492 ; Interspeech 2021, Aug 2021, Brno, Czech Republic. pp.1015-1018, ⟨10.21437/Interspeech.2021-1765⟩ (2021)
|
|
BASE
|
|
Show details
|
|
12 |
Resting functional connectivity in the semantic appraisal network predicts accuracy of emotion identification.
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Development of thalamus mediates paternal age effect on offspring reading: A preliminary investigation.
|
|
|
|
In: Human brain mapping, vol 42, iss 14 (2021)
|
|
BASE
|
|
Show details
|
|
14 |
Dataset of coronavirus content from Instagram with an exploratory analysis
|
|
|
|
In: ISSN: 2169-3536 ; EISSN: 2169-3536 ; IEEE Access ; https://hal.archives-ouvertes.fr/hal-03559489 ; IEEE Access, IEEE, 2021, 9, pp.157192-157202. ⟨10.1109/ACCESS.2021.3126552⟩ (2021)
|
|
BASE
|
|
Show details
|
|
15 |
Phoneme-to-Audio Alignment with Recurrent Neural Networks for Speaking and Singing Voice
|
|
|
|
In: Proceedings of Interspeech 2021 ; https://hal.archives-ouvertes.fr/hal-03552964 ; Proceedings of Interspeech 2021, International Speech Communication Association, Aug 2021, Brno, Czech Republic. pp.61-65, ⟨10.21437/interspeech.2021-1676⟩ ; https://www.interspeech2021.org/ (2021)
|
|
BASE
|
|
Show details
|
|
16 |
Improving Machine Translation of Arabic Dialects through Multi-Task Learning
|
|
|
|
In: 20th International Conference Italian Association for Artificial Intelligence:AIxIA 2021 ; https://hal.archives-ouvertes.fr/hal-03435996 ; 20th International Conference Italian Association for Artificial Intelligence:AIxIA 2021, Dec 2021, MILAN/Virtual, Italy (2021)
|
|
BASE
|
|
Show details
|
|
17 |
Document Domain Randomization for Deep Learning Document Layout Extraction
|
|
Ling, Meng; Chen, Jian; Möller, Torsten; Isenberg, Petra; Isenberg, Tobias; Sedlmair, Michael; Laramee, Robert,; Shen, Han-Wei; Wu, Jian; Giles, Clyde Lee
|
|
In: Proceedings of the 16th International Conference on Document Analysis and Recognition (ICDAR, September 5--10, Lausanne, Switzerland) ; https://hal.inria.fr/hal-03336444 ; Proceedings of the 16th International Conference on Document Analysis and Recognition (ICDAR, September 5--10, Lausanne, Switzerland), Sep 2021, Lausanne, Switzerland. pp.497-513, ⟨10.1007/978-3-030-86549-8_32⟩ (2021)
|
|
Abstract:
International audience ; We present document domain randomization (DDR), the first successful transfer of CNNs trained only on graphically rendered pseudo-paper pages to real-world document segmentation. DDR renders pseudo-document pages by modeling randomized textual and non-textual contents of interest, with userdefined layout and font styles to support joint learning of fine-grained classes. We demonstrate competitive results using our DDR approach to extract nine document classes from the benchmark CS-150 and papers published in two domains, namely annual meetings of Association for Computational Linguistics (ACL) and IEEE Visualization (VIS). We compare DDR to conditions of style mismatch, fewer or more noisy samples that are more easily obtained in the real world. We show that high-fidelity semantic information is not necessary to label semantic classes but style mismatch between train and test can lower model accuracy. Using smaller training samples had a slightly detrimental effect. Finally, network models still achieved high test accuracy when correct labels are diluted towards confusing labels; this behavior hold across several classes.
|
|
Keyword:
[SCCO.COMP]Cognitive science/Computer science; behavior analysis; Deep neural network; Document domain randomization; Document layout; evaluation
|
|
URL: https://hal.inria.fr/hal-03336444/file/docrandomization.pdf https://hal.inria.fr/hal-03336444 https://hal.inria.fr/hal-03336444/document https://doi.org/10.1007/978-3-030-86549-8_32
|
|
BASE
|
|
Hide details
|
|
18 |
End-to-End Speech Emotion Recognition: Challenges of Real-Life Emergency Call Centers Data Recordings
|
|
|
|
In: ISBN: 978-1-6654-0019-0 ; 2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII) ; https://hal.archives-ouvertes.fr/hal-03405970 ; 2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII), Sep 2021, Nara, Japan ; https://www.acii-conf.net/2021/ (2021)
|
|
BASE
|
|
Show details
|
|
|
|