Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Arabian Journal for Science and Engineering
Published in: Arabian Journal for Science and Engineering 11/2019

10-07-2019 | Research Article - Computer Engineering and Computer Science

Diacritics Effect on Arabic Speech Recognition

Authors: Sa’ed Abed, Mohammad Alshayeji, Sari Sultan

Published in: Arabian Journal for Science and Engineering | Issue 11/2019

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Arabic is the native language for over 300 million speakers and one of the official languages in United Nations. It has a unique set of diacritics that can alter a word’s meaning. Arabic automatic speech recognition (ASR) received little attention compared to other languages, and researches were oblivious to the diacritics in most cases. Omitting diacritics circumscribes the Arabic ASR system’s usability for several applications such as voice-enabled translation, text to speech, and speech-to-speech. In this paper, we study the effect of diacritics on Arabic ASR systems. Our approach is based on building and comparing diacritized and nondiacritized models for different corpus sizes. In particular, we build Arabic ASR models using state-of-the-art technologies for 1, 2, 5, 10, and 23 h. Each of those models was trained once with a diacritized corpus and another time with a nondiacritized version of the same corpus. KALDI toolkit and SRILM were used to build eight models for each corpus that are GMM-SI, GMM SAT, GMM MPE, GMM MMI, SGMM, SGMM-bMMI, DNN, DNN-MPE. Eighty different models were created using this experimental setup. Our results show that Word Error Rates (WERs) ranged from 4.68% to 42%. Adding diacritics increased WER by 0.59% to 3.29%. Although diacritics increased WERs, it is recommended to include diacritics for ASR systems when integrated with other systems such as voice-enabled translation. We believe that the benefit of the overall accuracy of the integrated system (e.g., translation) outweighs the WER increase for the Arabic ASR system.
previous article Unsupervised Shape Co-segmentation Based on Transformation Network
next article Non-singular Terminal Sliding Mode Control of Robot Manipulators with Trajectory Tracking Performance

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now
Literature
1.
Davis, S.; Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28(4), 357–366 (1980)CrossRef
2.
Hermansky, H.: Perceptual linear predictive (PLP) analysis of speech. J. Acoust. Soc. Am. 87(4), 1738–1752 (1990)CrossRef
3.
Rabiner, L.; Juang, B.: An introduction to hidden markov models. IEEE ASSP Mag. 3(1), 4–16 (1986)CrossRef
4.
Dong, Y.; Deng, L.: Automatic Speech Recognition. Springer, Berlin (2012)MATH
5.
Dahl, G.E.; Dong, Y.; Deng, L.; Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1), 30–42 (2012)CrossRef
6.
Hinton, G.; Deng, L.; Dong, Y.; Dahl, G.E.; Mohamed, A.; Jaitly, N.; Senior, A.; Vanhoucke, V.; Nguyen, P.; Sainath, T.N.; et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82–97 (2012)CrossRef
7.
Seide, F.; Li, G.; Yu, D.: Conversational speech transcription using context-dependent deep neural networks. In: Interspeech, pp. 437–440 (2011)
8.
9.
10.
11.
Stolcke, A.; et al.: Srilm-an extensible language modeling toolkit. In: Interspeech, vol. 2002, p. 2002 (2002)
12.
13.
14.
Kirchhoff, K.; Bilmes, J.; Henderson, J.; Schwartz, R.; Noamany, M.; Schone, P.; Ji, G.; Das, S.; Egan, M.; He, F. et al.: Novel speech recognition models for Arabic. In: Johns-Hopkins University Summer Research Workshop (2002)
15.
Alghamdi, M.; Elshafei, M.; Al-Muhtaseb, H.: Arabic broadcast news transcription system. Int. J. Speech Technol. 10(4), 183–195 (2007)CrossRef
16.
Abushariah, M.A.M.; Ainon, R.N.; Zainuddin, R.; Elshafei, M.; Khalifa, O.O.: Natural speaker-independent arabic speech recognition system based on hidden Markov models using sphinx tools. In: International Conference on Computer and Communication Engineering (ICCCE), pp. 1–6 (2010)
17.
Abushariah, M.A.A.M.; Ainon, R.; Zainuddin, R.; Elshafei, M.; Khalifa, O.O.: Arabic speaker-independent continuous automatic speech recognition based on a phonetically rich and balanced speech corpus. Int. Arab J. Inf. Technol. (IAJIT) 9(1), 84–93 (2012)
18.
Abushariah, M.A.M.; Ainon, R.N.; Zainuddin, R.; Elshafei, M.; Khalifa, O.O.: Phonetically rich and balanced speech corpus for arabic speaker-independent continuous automatic speech recognition systems. In: 10th International Conference on Information Sciences Signal Processing and their Applications (ISSPA), pp. 65–68 (2010)
19.
Hyassat, H.; Zitar, R.A.: Arabic speech recognition using sphinx engine. Int. J. Speech Technol. 9(3–4), 133–150 (2006)CrossRef
20.
Ali, A.; Zhang, Y.; Cardinal, P.; Dahak, N.; Vogel, S.; Glass, J.: A complete kaldi recipe for building Arabic speech recognition systems. In: Spoken Language Technology Workshop (SLT), IEEE, pp. 525–529 (2014)
21.
Ali, A.; Vogel, S.; Renals, S.: Speech recognition challenge in the wild: Arabic MGB-3. In: IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 316–322 (2017)
22.
23.
Woodland, P.C.: Speaker adaptation for continuous density hmms: A review. In: ISCA Tutorial and Research Workshop (ITRW) on Adaptation Methods for Speech Recognition, pp. 11–19 (2001)
24.
Anastasakos, T.; McDonough, J.; Schwartz, R.; Makhoul; J.: A compact model for speaker-adaptive training. In: Proceedings of Fourth International Conference on Spoken Language, ICSLP 96. vol. 2, pp. 1137–1140 (1996)
25.
Pye, D.; Woodland, P.C.: Experiments in speaker normalisation and adaptation for large vocabulary speech recognition. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, 1997. ICASSP-97, vol. 2, pp. 1047–1050 (1997)
26.
Gauvain, J.-L.; Lee, C.-H.: Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Trans. Speech Audio Process. 2(2), 291–298 (1994)CrossRef
27.
Leggetter, C.J.; Woodland, P.C.: Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Comput. Speech Lang. 9(2), 171–185 (1995)CrossRef
28.
Shinoda, K.: Speaker adaptation techniques for automatic speech recognition. In: Proceeding of APSIPA ASC (2011)
29.
Titus Felix Furtună: Dynamic programming algorithms in speech recognition. Revista Informatica Economică nr 2(46), 94–99 (2008)
30.
Chakraborty, C.; Talukdar, P.H.: Issues and limitations of hmm in speech processing: a survey. Int. J. Comput. Appl. 141(7), 13–17 (2016)
31.
Melnikoff, S.J.; Quigley, S.F.; Russell, M.J.: Implementing a hidden Markov model speech recognition system in programmable logic. In: International Conference on Field Programmable Logic and Applications, pp. 81–90. Springer, Berlin (2001)
32.
Rabiner, L.R.: A tutorial on hidden markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257–286 (1989)CrossRef
33.
Holmes, W.: Speech Synthesis and Recognition. CRC Press, Boca Raton (2001)
34.
Swee, L.H.: Implementing speech-recognition algorithms on the TMS320C2xx platform (1988)
35.
Buchsbaum, A.L.; Giancarlo, R.: Algorithmic aspects in speech recognition: an introduction. J. Exp. Algorithm. (JEA) 2, 1 (1997)MathSciNetCrossRef
36.
Satori, H.: Arabic speech recognition system based on CMUSphinx, pp. 28–35 (2007)
37.
38.
Hinton, G.; Deng, L.; Yu, D.; Dahl, G.E.; Mohamed, A.; Jaitly, N.; Senior, A.; Vanhoucke, V.; Nguyen, P.; Sainath, T.N.; Kingsbury, B.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82–97 (2012). https://​doi.​org/​10.​1109/​MSP.​2012.​2205597. ISSN 1053-5888CrossRef
39.
Saeed, K.; Nammous, M.: Heuristic method of Arabic speech recognition. In: Proceedings of IEEE 7th International Conference on DSPA, pp. 528–530 (2005)
40.
41.
Yu, D.; Deng, L.; Dahl, G.: Roles of pre-training and fine-tuning in context-dependent DBN-HMMS for real-world speech recognition. In: Proceedings of NIPS Workshop on Deep Learning and Unsupervised Feature Learning (2010)
42.
Deng, L.; Li, J.; Huang, J.-T.; Yao, K.; Yu, D.; Seide, F.; Seltzer, M.; Zweig, G.; He, X.; Williams, J. et al.: Recent advances in deep learning for speech research at microsoft. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 8604–8608 (2013)
43.
Nielsen, J.: Usability Engineering, 1st edn. Morgan Kaufmann, Burlington (1994)MATH
44.
45.
Povey, D.; Ghoshal, A.; Boulianne, G.; Burget, L.; Glembek, O.; Goel, N.; Hannemann, M.; Motlicek, P.; Qian, Y.; Schwarz, P. et al.: The kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding, number EPFL-CONF-192584. IEEE Signal Processing Society (2011)
46.
Allauzen, C.; Riley, M.; Schalkwyk, J.; Skut, W.; Mohri, M.: Openfst: a general and efficient weighted finite-state transducer library. In: International Conference on Implementation and Application of Automata, pp. 11–23. Springer, Berlin (2007)
47.
Gales, M.; Young, S.: The application of hidden Markov models in speech recognition. Found. Trends Signal Process. 1(3), 195–304 (2008)CrossRefMATH
48.
Gales, M.J.F.: Discriminative models for speech recognition. In: 2007 Information Theory and Applications Workshop, pp. 170–176 (2007)
49.
Tremain, T.E.: The government standard linear predictive coding algorithm: LPC-10. Speech Technol. 1(2), 40–49 (1982)
50.
Biadsy, F.; Moreno, P.J.; Jansche, M.: Google’s cross-dialect arabic voice search. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4441–4444 (2012)
51.
Vergyri, D.; Kirchhoff, K.: Automatic diacritization of Arabic for acoustic modeling in speech recognition. In: Proceedings of the Workshop On Computational Approaches to Arabic Script-based Languages, pp. 66–73. Association for Computational Linguistics (2004)
52.
Vergyri, D.; Kirchhoff, K.; Duh, K.; Stolcke, A.: Morphology-based language modeling for Arabic speech recognition. INTERSPEECH 4, 2245–2248 (2004)
53.
Soltau, H.; Saon, G.; Kingsbury, B.; Kuo, J.; Mangu, L.; Povey, D.; Zweig, G.: The IBM 2006 gale Arabic ASR system. In: IEEE International Conference on Acoustics, Speech and Signal Processing-ICASSP’07, vol. 4, pp. IV–349–IV–352 (2007)
54.
Djellab, M.; Amrouche, A.; Bouridane, A.; Mehallegue, N.: Algerian modern colloquial arabic speech corpus (AMCASC): regional accents recognition within complex socio-linguistic environments. Lang. Resour. Eval. 51(3), 613–641 (2017)CrossRef
55.
Mohammed, Z.Y.; Khidhir, A.S.M.: Real-time Arabic speech recognition. Int. J. Comput. Appl. 81(4), 43–45 (2013)
56.
Alkhatib, B.; Kawas, M.; Alnahhas, A.; Bondok, R.; Kannous, R.: Building an assistant mobile application for teaching Arabic pronunciation using a new approach for Arabic speech recognition. J. Theor. Appl. Inf. Technol. 95(3), 478 (2017)
57.
Gorin, A.L.; Riccardi, G.; Wright, J.H.: How may I help you? Speech Commun. 23(1), 113–127 (1997)CrossRefMATH
58.
Price, M.; Glass, J.; Chandrakasan, A.P.: A 6 mw, 5000-word real-time speech recognizer using wfst models. IEEE J. Solid-State Circuits 50(1), 102–112 (2015)CrossRef
59.
Elmisery, F.A.; Khalil, A.H.; Salama, A.E.; Hammed, H.F.: A FPGA-based hmm for a discrete Arabic speech recognition system. In: Proceedings of the 15th International Conference on Microelectronics, 2003. ICM 2003, pp. 322–325 (2003)
60.
Alghamdi, M.; Muzaffar, Z.; Alhakami, H.: Automatic restoration of arabic diacritics: a simple, purely statistical approach. Arab. J. Sci. Eng. 35(2), 125 (2010)
61.
62.
Duda, R.O.; Hart, P.E.; Stork, D.G.: Pattern Classification, 2nd edn. Wiley, New York (2001)MATH
63.
Rath, S.P.; Povey, D.; Veselỳ, K.; Cernockỳ, J.: Improved feature processing for deep neural networks. In: INTERSPEECH, pp. 109–113 (2013)
64.
Gopinath, R.A.: Maximum likelihood modeling with Gaussian distributions for classification. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 2, pp. 661–664 (1998)
65.
Gales, M.J.F.: Semi-tied covariance matrices for hidden Markov models. IEEE Trans. Speech Audio Process. 7(3), 272–281 (1999)CrossRef
66.
Povey, D.; Saon, G.: Feature and model space speaker adaptation with full covariance Gaussians. In: INTERSPEECH, pp. 1145–1148 (2006)
67.
Gales, M.J.F.: Maximum likelihood linear transformations for HMM-based speech recognition. Comput. Speech Lang. 12(2), 75–98 (1998)CrossRef
Metadata
Title
Diacritics Effect on Arabic Speech Recognition
Authors
Sa’ed Abed
Mohammad Alshayeji
Sari Sultan
Publication date
10-07-2019
Publisher
Springer Berlin Heidelberg
Published in
Arabian Journal for Science and Engineering / Issue 11/2019
Print ISSN: 2193-567X
Electronic ISSN: 2191-4281
DOI
https://doi.org/10.1007/s13369-019-04024-0

Other articles of this Issue 11/2019

Arabian Journal for Science and Engineering 11/2019 Go to the issue

Research Article - Computer Engineering and Computer Science

Approximate Proximal Gradient-Based Correlation Filter for Target Tracking in Videos: A Unified Approach

Research Article - Computer Engineering and Computer Science

Cluster-Based Architecture Capable for Device-to-Device Millimeter-Wave Communications in 5G Cellular Networks

Research Article - Computer Engineering and Computer Science

Storage Node Allocation Methods for Erasure Code-based Cloud Storage Systems

Research Article - Computer Engineering and Computer Science

Implementation and Performance Analysis of True Random Number Generator on FPGA Environment by Using Non-periodic Chaotic Signals Obtained from Chaotic Maps

Research Article - Computer Engineering and Computer Science

A Deep Camouflage: Evaluating Android’s Anti-malware Systems Robustness Against Hybridization of Obfuscation Techniques with Injection Attacks

Research Article - Computer Engineering and Computer Science

Hybrid Cascade Forward Neural Network with Elman Neural Network for Disease Prediction

Premium Partners

    Image Credits