Syntactic Reanalysis in Language Models for Speech Recognition

Johannes Twiefel 1 Xavier Hinaut 1, 2 Stefan Wermter 1
1 KT - Knowledge Technology group [Hamburg]
Department of Informatics [Hamburg]
2 Mnemosyne - Mnemonic Synergy
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, IMN - Institut des Maladies Neurodégénératives [Bordeaux]
Abstract : State-of-the-art speech recognition systems steadily increase their performance using different variants of deep neural networks and postprocess the results by employing N-gram statistical models trained on a large amount of data coming from the general-purpose domain. While achieving an excellent performance regarding Word Error Rate (17.343% on our Human-Robot Interaction data set), state-of-the-art systems generate hypotheses that are grammatically incorrect in 57.316% of the cases. Moreover, if employed in a restricted domain (e.g. Human-Robot Interaction), around 50% of the hypotheses contain out-of-domain words. The latter are confused with similarly pronounced in-domain words and cannot be interpreted by a domain-specific inference system. The state-of-the-art speech recognition systems lack a mechanism that addresses syntactic correctness of hypotheses. We propose a system that can detect and repair grammatically incorrect or infrequent sentence forms. It is inspired by a computational neuroscience model that we developed previously. The current system is still a proof-of-concept version of a future neurobiologically more plausible neural network model. Hence, the resulting system postprocesses sentence hypotheses of state-of-the-art speech recognition systems, producing in-domain words in 100% of the cases, syntactically and grammatically correct hypotheses in 90.319% of the cases. Moreover, it reduces the Word Error Rate to 11.038%.
Type de document :
Communication dans un congrès
2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), Sep 2017, Lisbon, Portugal. 〈http://icdl-epirob.org/〉
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01558462
Contributeur : Xavier Hinaut <>
Soumis le : vendredi 7 juillet 2017 - 17:47:20
Dernière modification le : mercredi 30 mai 2018 - 16:53:01

Fichier

twiefel_ICDL_EpiRob_2017__gene...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01558462, version 2

Collections

Citation

Johannes Twiefel, Xavier Hinaut, Stefan Wermter. Syntactic Reanalysis in Language Models for Speech Recognition. 2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), Sep 2017, Lisbon, Portugal. 〈http://icdl-epirob.org/〉. 〈hal-01558462v2〉

Partager

Métriques

Consultations de la notice

390

Téléchargements de fichiers

143