LIA-RAG: a system based on graphs and divergence of probabilities applied to Speech-To-Text Summarization

2016/01/26 by Elvys Linhares Pontes, Juan‐Manuel Torres‐Moreno, Pontes, Elvys Linhares +4
Computer Science · #Natural Language Processing Techniques #Speech Recognition and Synthesis #Topic Modeling #cs.CL #cs.IR

paper · pdf · doi:10.48550/arxiv.1601.07124

7 pages, 2 figures, CCCS Multiling 2015 Workshop

arxiv created 2016/01/26 · arxiv updated 2016/01/27

Abstract

This paper aims to introduces a new algorithm for automatic speech-to-text summarization based on statistical divergences of probabilities and graphs. The input is a text from speech conversations with noise, and the output a compact text summary. Our results, on the pilot task CCCS Multiling 2015 French corpus are very encouraging

Related

• Towards End-to-end Speech-to-text Summarization
• Un résumeur à base de graphes, indépéndant de la langue
• Audio Summarization with Audio Features and Probability Distribution Divergence
• Résumé abstractif à partir d'une transcription audio
• Automatic Summarization System coupled with a Question-Answering System (QAAS)