Towards a French Smart-Home Voice Command Corpus: Design and NLU Experiments

Abstract : Despite growing interest in smart-homes, semantically annotated large voice command corpora for Natural Language development (NLU) are scarce, especially for languages other than English. In this paper, we present an approach to generate customizable synthetic corpora of semantically-annotated French commands for a smart-home. This corpus was used to train three NLU models-a triangular CRF, an attention-based RNN and the Rasa framework-evaluated using a small corpus of real users interacting with a smart home. While the attention model performs best on another large French dataset, on the small smart home corpus the models vary performance across to intent, slot and slot value classification. To the best of our knowledge, no other French corpus of semantically annotated voice commands is currently publicly available
Type de document :
Communication dans un congrès
Sojka P., Horák A., Kopeček I., Pala K. 21st International Conference on Text, Speech and Dialogue TSD 2018, Sep 2018, Brno, Czech Republic. Springer, 11107, pp.509-517, Lecture Notes in Computer Science, TSD 2018. 〈https://www.tsdconference.org/tsd2018/〉. 〈10.1007/978-3-030-00794-2_55〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01802758
Contributeur : Michel Vacher <>
Soumis le : mercredi 12 septembre 2018 - 11:22:41
Dernière modification le : jeudi 11 octobre 2018 - 08:48:03
Document(s) archivé(s) le : jeudi 13 décembre 2018 - 13:50:15

Fichier

2018_TSD_Desot_auteur.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Thierry Desot, Stefania Raimondo, Anastasia. Mishakova, François Portet, Michel Vacher. Towards a French Smart-Home Voice Command Corpus: Design and NLU Experiments. Sojka P., Horák A., Kopeček I., Pala K. 21st International Conference on Text, Speech and Dialogue TSD 2018, Sep 2018, Brno, Czech Republic. Springer, 11107, pp.509-517, Lecture Notes in Computer Science, TSD 2018. 〈https://www.tsdconference.org/tsd2018/〉. 〈10.1007/978-3-030-00794-2_55〉. 〈hal-01802758〉

Partager

Métriques

Consultations de la notice

145

Téléchargements de fichiers

82