Category: Séminaires

(English) Language and communication difficulties in children: issues and challenges

Désolé, cet article est seulement disponible en Anglais Américain.

(English) Verbal Multi Word Expressions identification on spoken transcription

Désolé, cet article est seulement disponible en Anglais Américain.

(English) Use of Transfer Learning for Automatic Dietary Monitoring through Throat Microphone Recordings

Désolé, cet article est seulement disponible en Anglais Américain.

(English) DeepLearn Lecture Series II

Désolé, cet article est seulement disponible en Anglais Américain.

(English) DeepLearn Lecture Series I

Désolé, cet article est seulement disponible en Anglais Américain.

Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition

Orateur: Adrien Dufraux Paper by Adrien Dufraux, Emmanuel Vincent, Awni Hannun, Armelle Brun, Matthijs Douze, submitted to ASRU 2019 Date: le 5 sep, 2019 à 10h30 – C005 tl;dr: Learn an ASR model from noisy transcriptions. At training time, we search better transcriptions by incorporating a noise model into a differentiable beam search algorithm. Résumé: The …

Lire la suite

Introduction of semantic information in speech recognition

Orateur : Stéphane Level Date : le 12 septembre 2019 à 10h30 – C005 Résumé : Automatic Speech Recognition (ASR) is a growing industry. Indeed, there is an increasing demand from the industry for recognition systems or voice commands. The industrial use of this technology requires to have reliable and performing methodology. Current automatic speech …

Lire la suite

Prochains séminaires

Pour consulter le planning, veuillez cliquer « Continue reading »

Lire la suite

Natural Language Processing: Online hate speech against migrants

Orateur : Ashwin Geet D’Sa Date : le 29 août 2019 à 10h30 – C005 Résumé : The spectacular expansion of the Internet led to the development of a new sector in the natural language processing field: automatic Hate Speech detection, as in many countries hate speech is prohibited. There is no clear and formal …

Lire la suite

Semi-supervised triplet loss based learning of ambient audio embeddings

Orateur : Nicolas Turpault Date : le 2 mai 2019 à 10h30 – C005 Résumé : Deep neural networks are particularly useful to learn relevant representations from data. Recent studies have demonstrated the potential of unsupervised representation learning for ambient sound analysis using various flavors of the triplet loss. They have compared this approach to …

Lire la suite