Abstract
Automatic Speech Recognition (ASR) has revolutionized human-machine interactions as it allows the use of speech as an input modality. Speech is easy, natural and it is a skill that most people possess in their respective languages. Therefore, speech technology contributes to the usability and inclusivity of applications. ASR in languages such as English is extensively developed as there are large amounts of relevant resources available such as audio or transcribed data. For languages which are under-resourced, such as Kreol Morisien, ASR is a monumental task. In this paper, an attempt at developing an ASR system in Kreol Morisien is described. The ASR system was developed for the health domain to enable the automatic recognition of medical symptoms in spoken Kreol. The data collection process included the manual creation of a list of 848 symptoms along with 4000 audio files. Using the created corpus, the acoustic model for Kreol recognition was built and trained. This paper also describes a user evaluation which was conducted in different environments. Findings showed that the accuracy of the acoustic model was mainly affected by the level of noise. The gender of the speaker and the pronunciation style (depending on the region where the speaker originates from) did not cause any significant difference in the performance of the acoustic model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yu, D., Deng, L.: Automatic Speech Recognition. Springer, London (2016)
De Vries, N.J., et al.: A smartphone-based ASR data collection tool for under-resourced languages. Speech Commun. 56, 119–131 (2014)
Neerincx, M.A., Cremers, A.H., Kessens, J.M., Van Leeuwen, D.A., Truong, K.P.: Attuning speech-enabled interfaces to user and context for inclusive design: technology, methodology and practice. Univ. Access Inf. Soc. 8(2), 109–122 (2009)
Lamel, L., Gauvain, J.L., Adda, G.: Lightly supervised and unsupervised acoustic model training. Comput. Speech Lang. 16(1), 115–129 (2002)
Noormamode, W., Gobin-Rahimbux, B., Peerboccus, M.: A speech engine for Mauritian Creole. In: Satapathy, S.C., Bhateja, V., Somanah, R., Yang, X.-S., Senkerik, R. (eds.) Information Systems Design and Intelligent Applications. AISC, vol. 863, pp. 389–398. Springer, Singapore (2019). https://doi.org/10.1007/978-981-13-3338-5_36
Aubeeluck, M., Bucktowar, U., Gooda Sahib-Kaudeer, N., Gobin-Rahimbux, B.: A smart mobile health application for mauritius. In: Satapathy, S.C., Bhateja, V., Somanah, R., Yang, X.-S., Senkerik, R. (eds.) Information Systems Design and Intelligent Applications. AISC, vol. 863, pp. 333–343. Springer, Singapore (2019). https://doi.org/10.1007/978-981-13-3338-5_31
Baker, P.: Kreol: a description of Mauritian Creole. C. Hurst, London (1972)
Wang, Y.Y., Yu, D., Ju, Y.C., Acero, A.: An introduction to voice search. IEEE Signal Process. Mag. 25(3), 28–38 (2008)
Milhorat, P., Schlögl, S., Chollet, G., Boudy, J., Esposito, A., Pelosi, G.: Building the next generation of personal digital assistants. In: 2014 1st International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), pp. 458–463. IEEE (2014)
Krauwer, S.: The basic language resource kit (BLARK) as the first milestone for the language resources roadmap. In: Proceedings of SPECOM 2003, pp. 8–15 (2003)
Berment, V.: Méthodes pour informatiser les langues et les groupes de langues peu dotées. Doctoral dissertation, Université Joseph-Fourier-Grenoble I (2004)
Besacier, L., Barnard, E., Karpov, A., Schultz, T.: Automatic speech recognition for under-resourced languages: A survey. Speech Commun. 56, 85–100 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Gooda Sahib-Kaudeer, N., Gobin-Rahimbux, B., Bahsu, B.S., Maghoo, M.F.A. (2019). Automatic Speech Recognition for Kreol Morisien: A Case Study for the Health Domain. In: Salah, A., Karpov, A., Potapova, R. (eds) Speech and Computer. SPECOM 2019. Lecture Notes in Computer Science(), vol 11658. Springer, Cham. https://doi.org/10.1007/978-3-030-26061-3_42
Download citation
DOI: https://doi.org/10.1007/978-3-030-26061-3_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-26060-6
Online ISBN: 978-3-030-26061-3
eBook Packages: Computer ScienceComputer Science (R0)