Výsledky vyhledávání - "Dominique Fohr"

DNN-based semantic rescoring models for speech recognition

Publikováno v: TSD 2021-24th International Conference on Text, Speech and Dialogue
TSD 2021-24th International Conference on Text, Speech and Dialogue, Sep 2021, Olomouc, Czech Republic
Text, Speech, and Dialogue ISBN: 9783030835262
TDS

International audience; In this work, we address the problem of improving an automatic speech recognition (ASR) system. We want to efficiently model long-term semantic relations between words and introduce this information through a semantic model. W

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::02764de7ddbbf8b1e70a39a6a7e69fab
https://hal.archives-ouvertes.fr/hal-03239211/document

Zobrazit plný text záznamu

Explaining Deep Learning Models for Speech Enhancement

Autor: Sunit Sivasankaran, Emmanuel Vincent, Dominique Fohr

Publikováno v: INTERSPEECH 2021
INTERSPEECH 2021, Aug 2021, Brno, Czech Republic
INTERSPEECH 2021, Aug 2021, Brno, Czech Republic. ⟨10.21437/Interspeech.2021-1764⟩

International audience; We consider the problem of explaining the robustness of neural networks used to compute time-frequency masks for speech enhancement to mismatched noise conditions. We employ the Deep SHapley Additive exPlanations (DeepSHAP) fe

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9f0e8c6b342f8c39c39ebff8ed0ca17e
https://doi.org/10.21437/interspeech.2021-1764

Zobrazit plný text záznamu

BERT-based Semantic Model for Rescoring N-best Speech Recognition List

Autor: Irina Illina, Dominique Fohr

Publikováno v: INTERSPEECH 2021
INTERSPEECH 2021, Aug 2021, Brno, Czech Republic
INTERSPEECH 2021, Aug 2021, Brno, Czech Republic. ⟨10.21437/Interspeech.2021-313⟩

International audience; This work aims to improve automatic speech recognition (ASR) by modeling long-term semantic relations. We propose to perform this through rescoring the ASR N-best hypotheses list. To achieve this, we propose two deep neural ne

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3769e5f32fa861f38c3dec5547d7bc22
https://hal.archives-ouvertes.fr/hal-03248881

Zobrazit plný text záznamu

Unsupervised Domain Adaptation in Cross-corpora Abusive Language Detection

Autor: Irina Illina, Dominique Fohr, Tulika Bose

Publikováno v: SocialNLP@NAACL
SocialNLP 2021-The 9th International Workshop on Natural Language Processing for Social Media
SocialNLP 2021-The 9th International Workshop on Natural Language Processing for Social Media, Jun 2021, Virtual, France

International audience; The state-of-the-art abusive language detection models report great in-corpus performance, but underperform when evaluated on abusive comments that differ from the training scenario. As human annotation involves substantial ti

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1b41d5198902051d7781f7713447ce8a
https://hal.inria.fr/hal-03204605

Zobrazit plný text záznamu

Exploring Conditional Language Model Based Data Augmentation Approaches for Hate Speech Classification

Autor: Dana Ruiter, Ashwin Geet D'Sa, Dietrich Klakow, Dominique Fohr, Irina Illina

Publikováno v: Text, Speech, and Dialogue ISBN: 9783030835262
TDS

Deep Neural Network (DNN) based classifiers have gained increased attention in hate speech classification. However, the performance of DNN classifiers increases with quantity of available training data and in reality, hate speech datasets consist of

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::fc7e000254a2e0a138b3697c711ab084
https://doi.org/10.1007/978-3-030-83527-9_12

Zobrazit plný text záznamu

Multiword Expression Features for Automatic Hate Speech Detection

Autor: Nicolas Zampieri, Dominique Fohr, Irina Illina

Publikováno v: Natural Language Processing and Information Systems ISBN: 9783030805982
NLDB

The task of automatically detecting hate speech in social media is gaining more and more attention. Given the enormous volume of content posted daily, human monitoring of hate speech is unfeasible. In this work, we propose new word-level features for

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::dff9511908155240fd19a58d7a51dde6
https://doi.org/10.1007/978-3-030-80599-9_14

Zobrazit plný text záznamu

Introduction of semantic model to help speech recognition

Autor: Stephane Level, Dominique Fohr, Irina Illina

Publikováno v: TSD 2020-Twenty-third International Conference on Text, Speech and Dialogue
TSD 2020-Twenty-third International Conference on Text, Speech and Dialogue, Sep 2020, Brno, Czech Republic
Text, Speech, and Dialogue ISBN: 9783030583224
TDS

International audience; Current Automatic Speech Recognition (ASR) systems mainly take into account acoustic, lexical and local syntactic information. Long term semantic relations are not used. ASR systems significantly decrease performance when the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ba97c7e482c3b4a9e66dc0f5eeec10f5
https://hal.science/hal-02862245

Zobrazit plný text záznamu

BERT and fastText Embeddings for Automatic Detection of Toxic Speech

Autor: Ashwin Geet D'Sa, Dominique Fohr, Irina Illina

Publikováno v: OCTA
SIIE 2020-Information Systems and Economic Intelligence; International Multi-Conference on:“Organization of Knowledge and Advanced Technologies”(OCTA)
SIIE 2020-Information Systems and Economic Intelligence; International Multi-Conference on:“Organization of Knowledge and Advanced Technologies”(OCTA), Feb 2020, Tunis, Tunisia

International audience; With the expansion of Internet usage, catering to the dissemination of thoughts and expressions of an individual, there has been an immense increase in the spread of online hate speech. Social media, community forums, discussi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8a633b697189bff809cf2a3d44bc2f14
https://doi.org/10.1109/octa49274.2020.9151853

Zobrazit plný text záznamu

Label Propagation-Based Semi-Supervised Learning for Hate Speech Classification

Autor: Dietrich Klakow, Irina Illina, Dana Ruiter, Ashwin Geet D'Sa, Dominique Fohr

Publikováno v: Insights
Insights from Negative Results Workshop, EMNLP 2020
Insights from Negative Results Workshop, EMNLP 2020, Nov 2020, Punta Cana, Dominican Republic

International audience; Research on hate speech classification has received increased attention. In real-life scenarios , a small amount of labeled hate speech data is available to train a reliable classifier. Semi-supervised learning takes advantage

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d1e8d5039978be5668b46c98defb2b73
https://doi.org/10.18653/v1/2020.insights-1.8

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání