End2End Acoustic to Semantic Transduction
Valentin Pelloin, Nathalie Camelin, Antoine Laurent, Renato De Mori, Antoine Caubrière, Yannick Estève, Sylvain Meignier
Abstract
In this paper, we propose a novel end-to-end sequence-to-sequence spoken language understanding model using an attention mechanism. It reliably selects contextual acoustic features in order to hypothesize semantic contents. An initial architecture capable of extracting all pronounced words and concepts from acoustic spans is designed and tested. With a shallow fusion language model, this system reaches a 13.6 concept error rate (CER) and an 18.5 concept value error rate (CVER) on the French MEDIA corpus, achieving an absolute 2.8 points reduction compared to the state-of-the-art. Then, an original model is proposed for hypothesizing concepts and their values. This transduction reaches a 15.4 CER and a 21.6 CVER without any new type of context.
BibTeX
@inproceedings{icassp2021_end2endacoustict,
title = {End2End Acoustic to Semantic Transduction},
author = {Valentin Pelloin and Nathalie Camelin and Antoine Laurent and Renato De Mori and Antoine Caubrière and Yannick Estève and Sylvain Meignier},
booktitle = {ICASSP 2021},
year = {2021}
}