| 1 |
Starting a new treebank? Go SUD! Theoretical and practical benefits of the Surface-Syntactic distributional approach
|
|
|
|
In: Sixth International Conference on Dependency Linguistics (Depling, SyntaxFest 2021) ; https://hal.inria.fr/hal-03509136 ; Sixth International Conference on Dependency Linguistics (Depling, SyntaxFest 2021), Mar 2022, Sofia, Bulgaria (2022)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Évaluation des propriétés multilingues d'un embedding contextualisé
|
|
|
|
In: EGC 2022 - Conférence francophone sur l'Extraction et la Gestion des Connaissances ; https://hal.archives-ouvertes.fr/hal-03578480 ; EGC 2022 - Conférence francophone sur l'Extraction et la Gestion des Connaissances, Jan 2022, Blois, France (2022)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Tackling Morphological Analogies Using Deep Learning -- Extended Version
|
|
|
|
In: https://hal.inria.fr/hal-03425776 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Unsupervised Word embedding Alignment in the biomedical domain ; Alignement non supervisé d'embeddings de mots dans le domaine biomédical
|
|
|
|
In: CIFSD - Conférence Internationale Francophone sur la Science des Données ; https://hal.archives-ouvertes.fr/hal-03259987 ; CIFSD - Conférence Internationale Francophone sur la Science des Données, Jun 2021, Marseille/Virtuel, France (2021)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Convertir le Trésor de la Langue Française en Ontolex-Lemon : un zeste de données liées
|
|
|
|
In: Journées LIFT 2021 - Linguistique informatique, formelle et de terrain ; https://hal.inria.fr/hal-03463294 ; Journées LIFT 2021 - Linguistique informatique, formelle et de terrain, Dec 2021, Grenoble, France (2021)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Study of non-projective dependencies in French ; Étude des dépendances syntaxiques non projectives en français
|
|
|
|
In: ISSN: 1248-9433 ; EISSN: 1965-0906 ; Revue TAL ; https://hal.inria.fr/hal-03389157 ; Revue TAL, ATALA (Association pour le Traitement Automatique des Langues), 2021, 62 (1) (2021)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
MRI Vocal Tract Sagittal Slices Estimation during Speech Production of CV
|
|
|
|
In: EUSIPCO 2020 - 28th European Signal Processing Conference ; https://hal.inria.fr/hal-03090824 ; EUSIPCO 2020 - 28th European Signal Processing Conference, Jan 2021, Amsterdam / Virtual, Netherlands ; https://eusipco2020.org/ (2021)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Multimodal dataset of real-time 2D and static 3D MRI of healthy French speakers
|
|
|
|
In: ISSN: 2052-4463 ; EISSN: 2052-4463 ; Scientific Data ; https://hal.archives-ouvertes.fr/hal-03507532 ; Scientific Data , Nature Publishing Group, 2021, 8 (1), pp.258. ⟨10.1038/s41597-021-01041-3⟩ (2021)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
On the Dual Interpretation of Nouns as Types and Predicates in Semantic Type Theories
|
|
|
|
In: 2nd Workshop on Computing Semantics with Types, Frames and Related Structures, ESSLLI 2021 ; https://hal.archives-ouvertes.fr/hal-03468606 ; 2nd Workshop on Computing Semantics with Types, Frames and Related Structures, ESSLLI 2021, Jul 2021, Virtual, Netherlands (2021)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Privacy and utility of x-vector based speaker anonymization
|
|
|
|
In: https://hal.inria.fr/hal-03197376 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Transformer versus LSTM Language Models Trained on Uncertain ASR Hypotheses in Limited Data Scenarios
|
|
|
|
In: https://hal.inria.fr/hal-03362828 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Enabling voice-based apps with European values
|
|
|
|
In: ISSN: 0926-4981 ; ERCIM News ; https://hal.inria.fr/hal-03476390 ; ERCIM News, ERCIM, 2021, 126, pp.38-39 ; https://ercim-news.ercim.eu/images/stories/EN126/EN126-web.pdf (2021)
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Enhancing Speech Privacy with Slicing
|
|
|
|
In: https://hal.inria.fr/hal-03369137 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Training RNN Language Models on Uncertain ASR Hypotheses in Limited Data Scenarios
|
|
|
|
In: https://hal.inria.fr/hal-03327306 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 15 |
Adapting Language Models When Training on Privacy-Transformed Data
|
|
|
|
In: INTERSPEECH 2021 ; https://hal.inria.fr/hal-03189354 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Privacy and utility of x-vector based speaker anonymization
|
|
|
|
In: https://hal.inria.fr/hal-03197376 ; 2021 (2021)
|
|
Abstract:
We study the scenario where individuals (speakers) contribute to the publication of an anonymized speech corpus. Data users then leverage this public corpus to perform downstream tasks (such as training automatic speech recognition systems), while attackers may try to de-anonymize itbased on auxiliary knowledge they collect. Motivated by this scenario, speaker anonymization aims to conceal the speaker identity while preserving the quality and usefulness of speech data. In this paper, we study x-vector based speaker anonymization, the leading approach in the recent Voice Privacy Challenge, which converts an input utterance into that of a random pseudo-speaker. We show that the strength of the anonymization varies significantly depending on how the pseudo-speaker is selected. In particular, we investigate four design choices: the distance measure between speakers, the region of x-vector space where the pseudo-speaker is mapped, the gender selection and whether to use speaker or utterance level assignment. We assess the quality of anonymization from the perspective of the three actors involved in our threat model, namely the speaker, the user and the attacker. To measure privacy and utility, we use respectively the linkability score achieved by the attackers and the decoding word error rate incurred by an ASR model trained with the anonymized data. Experiments on LibriSpeech dataset confirm that the optimal combination ofdesign choices yield state-of-the-art performance in terms of privacy protection as well as utility. Experiments on Mozilla Common Voice dataset show that the best design choices with 50 speakers guarantee the same anonymization level against re-identification attack as raw speech with 20,000 speakers.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; linkability; privacy; speaker anonymization; speaker identification; speech recognition; utility
|
|
URL: https://hal.inria.fr/hal-03197376v2/file/design_choices_informed.pdf
https://hal.inria.fr/hal-03197376
https://hal.inria.fr/hal-03197376v2/document
|
|
BASE
|
|
Hide details
|
|
|
| 17 |
Graph Matching and Graph Rewriting: GREW tools for corpus exploration, maintenance and conversion
|
|
|
|
In: EACL 2021 - 16th conference of the European Chapter of the Association for Computational Linguistics ; https://hal.inria.fr/hal-03177701 ; EACL 2021 - 16th conference of the European Chapter of the Association for Computational Linguistics, Apr 2021, Kiev/Online, Ukraine ; https://2021.eacl.org/ (2021)
|
|
BASE
|
|
Show details
|
|
|
| 18 |
Dialogue Modeling in a Dynamic Framework ; Modélisation dynamique des dialogues
|
|
|
|
In: https://hal.archives-ouvertes.fr/tel-03541628 ; Computation and Language [cs.CL]. Université de Lorraine; École doctorale IAEM Lorraine - Informatique, Automatique, Électronique - Électrotechnique, Mathématiques de Lorraine, 2021. English. ⟨NNT : 2021LORR0199⟩ (2021)
|
|
BASE
|
|
Show details
|
|
|
| 19 |
Using Silence MR Image to Synthesise Dynamic MRI Vocal Tract Data of CV
|
|
|
|
In: INTERSPEECH 2020 ; https://hal.inria.fr/hal-03090808 ; INTERSPEECH 2020, Oct 2020, Shangaï / Virtual, China ; http://www.interspeech2020.org/ (2020)
|
|
BASE
|
|
Show details
|
|
|
| 20 |
Introduction d’informations sémantiques dans un système de reconnaissance de la parole
|
|
|
|
In: Actes de la 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 1 : Journées d'Études sur la Parole ; 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 1 : Journées d'Études sur la Parole ; https://hal.archives-ouvertes.fr/hal-02798559 ; 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 1 : Journées d'Études sur la Parole, 2020, Nancy, France. pp.362-369 (2020)
|
|
BASE
|
|
Show details
|
|
|
|
|
