Abstract
Building an Automatic Speech Recognition (ASR) system requires a well segmented and labeled speech corpus (often transcription is made by an expert). These resources are not always available for languages such as Arabic. This paper presents a system for automatic Arabic speech segmentation for speech recognition purpose. State-of-the-art models in ASR systems are the Hidden Markov Models (HMM), so that for the segmentation, we expect the use of embedded learning approach where an alignment between speech segments and HMMs is done iteratively to refine the segmentation. This approach needs the use of transcribed and labelled data, for this purpose, we built a dedicated corpus. Finally, the obtained results are close to those described in the literature and could be improved by handling more Arabic speech specificities.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bahi, H., Sellami, M.: Combination of vector quantization and hidden Markov models for Arabic speech recognition. In: Proceedings ACS/IEEE International Conference on Computer Systems and Applications, Beirut, Liban, pp. 96–100 (2001)
Bahi, H., Sellami, M.: Neural expert model applied to phonemes recognition. In: Perner, P., Imiya, A. (eds.) MLDM 2005. LNCS (LNAI), vol. 3587, pp. 507–515. Springer, Heidelberg (2005)
Sangeetha, J., Jothilakshmi, S.: Robust automatic continuous speech segmentation for indian languages to improve speech to speech translation. Int. J. Comput. Appl. 53, 13–16 (2012)
Khawaja, M.A., Haider, N.G.: Segmentation of Sindhi speech using formants. In: IEEE International Conference on Signal Processing and Communications (ICSPC 2007), Dubai, United Arab Emirates, pp. 24–27 (2017)
Sharma, M., Mammone, R.J.: Blind speech segmentation: automatic segmentation of speech without linguistic knowledge. In: ICSLP (1996)
Wang, H., Lee, T.: Acoustic segment modeling with spectral clustering methods. IEEE/ACM Trans. Audio Speech Lang. Process. (TASLP), 264–277 (2015)
Brognaux, S., Drugman, T.: HMM-based speech segmentation: improvements of fully automatic approaches. IEEE/ACM Trans. Audio Speech Lang., 5–15 (2016)
Young, S., et al.: The HTK Book. Cambridge University Engineering Department, Cambridge (2002)
Galka, J., Ziolko, B.: Study of performance evaluation methods for non-uniform speech segmentation. Int. J. Circ. Syst. Sig. Process. (2007)
Nofal, M., Abdel-Raheem, E., Henawy, H.E., Kader, N.S.A.: Arabic automatic segmentation system and its application for Arabic speech recognition system. In: IEEE 46th Midwest Symposium on Circuits and Systems, vol. 2, pp. 697–700 (2003)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Frihia, H., Bahi, H. (2016). Embedded Learning Segmentation Approach for Arabic Speech Recognition. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds) Text, Speech, and Dialogue. TSD 2016. Lecture Notes in Computer Science(), vol 9924. Springer, Cham. https://doi.org/10.1007/978-3-319-45510-5_44
Download citation
DOI: https://doi.org/10.1007/978-3-319-45510-5_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-45509-9
Online ISBN: 978-3-319-45510-5
eBook Packages: Computer ScienceComputer Science (R0)