Benoît Favre

ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks

2022 · arXiv (Cornell University)

We aim at improving spoken language modeling (LM) using very large amount of automatically transcribed speech. We leverage the INA (French National Audiovisual Institute) collection and obtain 19GB of text after applying ASR on 350,000 …

Reducing named entity hallucination risk to ensure faithful summary generation

2023

International audience

Word Embedding Evaluation and Combination

2016

Word embeddings have been successfully used in several natural language processing tasks (NLP) and speech processing.Different approaches have been introduced to calculate word embeddings through neural networks.In the literature, many studies focused on word embedding …