Investigating the Impact of Gender Representation in ASR Training Data: a Case Study on Librispeech

no code implementations • ACL (GeBNLP) 2021 • Mahault Garnerin, Solange Rossato, Laurent Besacier

In this paper we question the impact of gender representation in training data on the performance of an end-to-end ASR system.

Repr\'esentation du genre dans des donn\'ees open source de parole (Gender representation in open source speech resources 1 With the rise of artificial intelligence (AI) and the growing use of deep-learning architectures, the question of ethics and transparency in AI systems has become a central concern within the research community)

no code implementations • JEPTALNRECITAL 2020 • Mahault Garnerin, Solange Rossato, Laurent Besacier

Avec l{'}essor de l{'}intelligence artificielle (IA) et l{'}utilisation croissante des architectures d{'}apprentissage profond, la question de l{'}{\'e}thique et de la transparence des syst{\`e}mes d{'}IA est devenue une pr{\'e}occupation centrale au sein de la communaut{\'e} de recherche.

Ethics

Pratiques d'\'evaluation en ASR et biais de performance (Evaluation methodology in ASR and performance bias)

no code implementations • JEPTALNRECITAL 2020 • Mahault Garnerin, Solange Rossato, Laurent Besacier

Nous proposons une r{\'e}flexion sur les pratiques d{'}{\'e}valuation des syst{\`e}mes de reconnaissance automatique de la parole (ASR).

Gender Representation in Open Source Speech Resources

no code implementations • LREC 2020 • Mahault Garnerin, Solange Rossato, Laurent Besacier

With the rise of artificial intelligence (AI) and the growing use of deep-learning architectures, the question of ethics, transparency and fairness of AI systems has become a central concern within the research community.

Ethics Fairness

Gender Representation in French Broadcast Corpora and Its Impact on ASR Performance

no code implementations • 23 Aug 2019 • Mahault Garnerin, Solange Rossato, Laurent Besacier

The disparity of available data for both gender causes performance to decrease on women.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

MaSS: A Large and Clean Multilingual Corpus of Sentence-aligned Spoken Utterances Extracted from the Bible

1 code implementation • LREC 2020 • Marcely Zanon Boito, William N. Havard, Mahault Garnerin, Éric Le Ferrand, Laurent Besacier

However, the fact that the source content (the Bible) is the same for all the languages is not exploited to date. Therefore, this article proposes to add multilingual links between speech segments in different languages, and shares a large and clean dataset of 8, 130 parallel spoken utterances across 8 languages (56 language pairs).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4