Abstract
The present work is a part of the realization of the Arabic vocal server SARF (Bahou 2014). Indeed, in this paper we propose a numerical learning-based method for the oral Arabic complex disfluencies processing. The proposed method allows, from a pretreated and semantically labeled utterance, to delimit and label the conceptual segments of a spontaneous Arabic oral utterance. Then, it allows, from a segmented utterance, to detect and delimit the disfluent segments in order to correct them. The result of the implementation of this method is the Complex Disfluencies Processing Module (CDPM). For the evaluation of our CDPM, we found satisfactory results with an F-measure equal to 91.9%. After integrating the CDPM into the SARF system, we achieved an improvement of 11.88% in acceptable understanding and 3.77% in error rate. This improvement proves the effectiveness of the numerical learning-based method in the oral Arabic complex disfluencies processing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The translate Arabic example is based on Buckwalter Transliteration.
References
Bahou, Y.: Compréhension Automatique de la Parole Arabe Spontanée: Intégration dans un Serveur Vocal Interactif. PhD Thesis, Faculté des Sciences économiques et de Gestion de Sfax (2014)
Bahou, Y., Maâloul, M.H., Abbassi, H.: Hybrid approach for conceptual segmentation of spontaneous Arabic oral utterances. In: 3rd International Conference on Arabic Computational Linguistics (ACLing’17), Dubai, UAE (2017a)
Bahou, Y., Maâloul, M.H., Boughariou, E.: Towards the supervised machine learning and the conceptual segmentation technique in the spontaneous Arabic speech understanding. In: 3rd International Conference on Arabic Computational Linguistics (ACLing’17), Dubai, UAE (2017b)
Bahou, Y., Masmoudi, A., Hadrich-Belguith L.: Traitement des disfluences dans le cadre de la compréhension automatique de l’oral arabe spontané. 28èmes Journées d’Études sur la Parole (JEP’10), Mons, Belgique (2010)
Bear, J., Dowding, J., Shriberg, E.: Integrating multiple knowledge sources for detection and correction of repairs in human-computer dialog. In: Proceedings of the 30th Annual Meeting of the Association for Computational Linguistics (ACL’92), Newark, Deleware (1992)
Boughariou, E., Bahou, Y., Maâloul, M.H.: Application d’une méthode numérique à base d’apprentissage pour la segmentation conceptuelle de l’oral arabe spontané. In: Proceedings of the 29th International Business Information Management Association (IBIMA’17), Vienna, Austria (2017)
Christodoulides, G., Avanzi, M.: Automatic Detection and Annotation of Disfluencies in Spoken French Corpora. Institute for Language & Communication, University of Louvain, Belgium DTAL, Faculty of Modern & Medieval Languages, University of Cambridge, UK (2015)
Constant, M., Dister, A.: Les disfluences dans les mots composés. Journées sur l’Analyse des Données Textuelles (JADT’12), Belgium (2012)
Ferreira, F., Lau, E., Bailey, K.: Disfluencies, language comprehension, and Tree Adjoining Grammars. Cogn. Sci. 28(5), 721–749 (2004)
Honal, M.: Correction of Disfluencies in spontaneous speech using a noisy-channel approach. PhD thesis, University of Karlsruhe, Karlsruhe, Germany (2003)
Kaushik, M., Trinkle, M., Hashemi-Sakhtsari, A.: Automatic detection and removal of disfluencies from spontaneous speech. In: School of Electrical and Electronic Engineering. The University of Adelaide, Adelaide, South Australia. C3I Division, Defense Science and Technology Organization, Edinburgh, South Australia (2010)
Kim, J.: Automatic detection of sentence boundaries, disfluencies, and conversational fillers in spontaneous speech. PhD thesis, University of Washington (2004)
Labiadh, M., Bahou, Y., Maâloul, M.H.: Complex disfluencies processing in spontaneous Arabic speech. In: Proceeding of International Workshop on Language Processing and Knowledge Management (LPKM’18), Sfax, Tunisia (2018a)
Labiadh, M., Bahou, Y., Maâloul, M.H.: Numerical learning-based method for the automatic processing of complex disfluencies in spontaneous Arabic speech. In: Proceeding of Joint Conference on Computing (JCCO’18), Hammamet, Tunisia (2018b)
Lease, M., Johnson, M., Charniak, E.: Recognizing disfluencies in conversational speech. IEEE Trans. Audio, Speech, Lang. Process. 14(5), 1566–1573 (2006)
Proença, J., Lopes, C., Tjalve, M., Stolcke, A., Candeias, S., Perdigão, F.: Automatic evaluation of reading aloud performance in children. Department of Electrical and Computer Engineering. University of Coimbra, Portugal, (2017)
Qader, R., Lecorvé, G., Lolive, D., Sébillot, P.: Ajout automatique de disfluences pour la synthèse de la parole spontanée: formalisation et preuve de concept. Traitement Automatique du Langage Naturel (TALN’17), Orléans, France (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Majda, L., Younès, B., Maâloul, M.H. (2020). Automatic Processing of Oral Arabic Complex Disfluencies. In: Bouhlel, M., Rovetta, S. (eds) Proceedings of the 8th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT’18), Vol.1. SETIT 2018. Smart Innovation, Systems and Technologies, vol 146. Springer, Cham. https://doi.org/10.1007/978-3-030-21005-2_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-21005-2_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-21004-5
Online ISBN: 978-3-030-21005-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)