Abstract The standard Arabic language, like many other languages, contains a prosodic feature, which is hidden in the speech signal. The studies related to this field are still in the preliminary stages. This fact results in restraining the performance of the communication tools. The prosodic study allows people having all the communication tools needed in their native language. Therefore, we propose, in this paper, a prosodic study between the various types of sentences in the standard Arabic language. The sentences are recognized according to three modalities as the following: declarative, interrogative and exclamatory sentences. The results of this study will be used to synthesize the different types of pronunciation that can be exploited in several domains namely the man-machine communication. To this end, we developed a specific dataset, consisting of the three types of sentences. Then, we tested two sets of features: prosodic features (Fundamental Frequency, Energy and Duration) and spectrum features (Mel-Frequency Cepstral Coefficients and Linear Predictive Coding) as well their combination. We adopted the Multi-Class Support Vector Machine (MC-SVM) as classifier. The experimental results are very encouraging.

References

[1] American Univ in Cairo, Modern Standard Arabic Vocab Clinic, American University in Cairo Press, 2005.

[2] Awasthy N., Saini J., and Chauhan D., “Spectral Analysis of Speech: A New Technique,” International Journal of Electrical, Computer, Energetic, Electronic and Communication Engineering, vol. 2, no. 7, pp. 1517-1526, 2008.

[3] Bänziger T. and Scherer K., “The Role of Intonation in Emotional Expressions,” Speech Communication, vol. 46, no. 3-4, pp. 252-267, 2005.

[4] Bazillon T., Maza B., Rouvier M., Bechet F., and Nasr F., “Speaker Role Recognition Using Question Detection and Characterization,” in Proceedings of INTERSPEECH, Florence, pp. 1333-1336, 2011.

[5] Bishop C., Pattern Regression and Machine Learning, Springer, 2006.

[6] Blanchard N., Donnelly P., Olney A., Samei B., Ward B., Sun X., Kelly S., Nystrand M., and D’Mello S., “Identifying Teacher Questions Using Automatic Speech Recognition in Classrooms,” in Proceedings of the SIGDIAL, Los Angeles, pp. 191-201, 2016.

[7] Boakye K., Favre B., and Hakkani-tur D., “Any Questions? Automatic Question Detection in Meetings,” in Proceedings of IEEE Workshop in Automatic Speech Recognition and Understanding, Merano, pp. 485-489, 2009.

[8] Chamasemani F. and Singh Y., “Multi-Class Support Vector Machine (SVM) Classifiers-An Application in Hypothyroid Detection and Classification,” in Proceedings of Bio-Inspired Computing: Theories and Applications 6th International Conference Proceedings, Penang, pp. 351-356, 2011.

[9] Cristianini N. and Shawe-Taylor J., An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods, Cambridge University Press, 2000.

[10] Hagen A., Connors D., and Pellm B., “The Analysis and Design of Architecture Systems for Speech Secognition on Modern Handheld- Computing Devices,” in Proceedings of 1st IEEE/ACM/IFIP International Conference, Newport Beach, pp. 65-70, 2003.

[11] Halimouche R., Teffahi H., and Falek L., “Detection of Questions in Berber Language Using Prosodic Features,” in Proceedings of International Conference on Multimedia Computing and Systems, Marrakech, pp. 197- 200, 2014.

[12] Hasan M., Doddipatla R., and Hain T., “Multi- Pass Sentence-End Detection of Lecture Speech,” in Proceedings of INTERSPEECH, Singapore, pp. 2902-2906, 2014.

[13] Hsu C. and Lin C., “A Comparison of Methods for Multiclass Support Vector Machines,” IEEE Transactions on Neural Networks, vol. 13, no. 2, pp. 415-425, 2002.

[14] Khan O., Al-Khatib W., and Cheded L., “A Preliminary Study of Prosody-Based Detection of Questions in Standard Arabic Language Speech Monologues,” The Arabian Journal for Science and Engineering, vol. 35, no. 2C, pp. 167-181, 2010.

[15] Kolář J. and Liu Y., “Automatic Sentence Boundary Detection in Conversational Speech: A Cross-Lingual Evaluation on English and Czech,” in Proceedings of IEEE International Detecting Sentences Types in the Standard Arabic Language 921 Conference on Acoustics, Speech and Signal Processing, Dallas, pp. 5258-5261, 2010.

[16] Lee C. and Narayanan S., “Toward Detecting Emotions in Spoken Dialogs,” IEEE Transactions on Speech and Audio Processing, vol. 13, no. 2, pp. 293-303, 2005.

[17] Liscombe J., Venditti J., and Hirschberg J., “Detecting Question-Bearing Turns in Spoken Tutorial Dialogues,” in Proceedings of the International Conference of Spoken Language Processing, 2006.

[18] Liu Y., Shriberg E., Stolcke A., Hillard D., Ostendorf M., and Harper M., “Enriching Speech Recognition With Automatic Detection of Sentence Boundaries and Disfluencies,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 14, no. 5, pp. 1526-1540, 2006.

[19] Margolis A. and Ostendorf M., “Question Detection In Spoken Conversations Using Textual Conversations,” in Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Short Papers, Portland, pp. 118-124, 2011.

[20] Moniz H., Batista F., Trancoso I., and Mata A., “Analysis of Interrogatives in Different Domains,” in Proceedings of the 3rd International Training School Conference on Toward Autonomous, Adaptive, and Context-Aware Multimodal Interfaces: Theoretical and Practical Issues, Caserta, pp. 134-146, 2010.

[21] Motlíček P., Feature Extraction in Speech Coding and Recognition, Oregon Graduate Institute of Science and Technology, 2002.

[22] Muda L., Begam M., and Elamvazuthi I., “Voice Recognition Algorithms Using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques,” Journal of Computing, vol. 2, no. 3, pp. 138-143, 2010.

[23] Raj S., Rehman Z., Rauf S., Siddique R., and Anwar W., “An Artificial Neural Network Approach for Sentence Boundary Disambiguation in Urdu Language Text,” The International Arab Journal of Information Technology, vol. 12, no. 4, pp. 395-400, 2015.

[24] Rosset S., Tribout D., and Lamel L., “Multi- Level Information and Automatic Dialog Acts Detection in Human-Human Spoken Dialogs,” Speech Communication, vol. 50, no. 1, pp. 1-13, 2008.

[25] Shriberg E., Stolcke A., Jurafsky D., Coccaro N., Meteer M., Bates R., Taylor P., Ries K., Martin R., and Dykema C., “Can Prosody Aid the Automatic Classification of Dialog Dcts in Conversational Speech?,” Language and Speech, vol. 41, no. 3-4, pp. 443-492, 1998.

[26] Sinha P., Speech Processing in Embedded Systems, Springer, 2010.

[27] Stolcke A., Coccaro N., Bates R., Taylor P., Ess- Dykema C., Ries K., Shriberg E., Jurafsky D., Martin R., and Meteer M., “Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech,” Journal Computational Linguistics, vol. 26, no. 3, pp. 339-373, 2000.

[28] Varpe D., Sawant N., Shah S., Shivarkar S., and Pawar P., “Improve HCII by Using Gender and Emotion Recognition Using Speech Signal: A Survey,” International Journal of Advanced Research, vol. 4, no. 3, pp. 1344-1347, 2016.

[29] Venditti J., Hirschberg J., and Liscombe J., “Intonational Cues To Student Questions in Tutoring Dialogs,” in Proceedings of INTERSPEECH, Pittsburgh, pp. 549-552, 2006.

[30] Ververidis D., Kotropoulos C., and Pitas I., “Automatic Emotional Speech Classification,” in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, Montreal, pp. 1-593, 2004.

[31] Yuan J. and Jurafsky D., “Detection of Questions in Chinese Conversational Speech,” in Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding, San Juan, pp. 47-52, 2005.

[32] Yuan J., Shih C., and Kochanski G., “Comparison of Declarative and Interrogative Intonation in Chinese,” in Proceedings of Speech Prosody, Aix-en Provence, 2002. Ramzi Halimouche is PhD student in telecommunication and information processing at the university of Science and Technology Houari Boumediene in Algiers Algeria he has a Master's degree in Intelligent and communicates systems. Currently he is working on the influence of prosody on dialogue acts. In particular, the automatic classification of interrogative and affirmative sentences, the analysis parameters and adequate classifiers. Hocine Teffahi received his Magister and doctoral in electrical engennering from the University of Science and Technology Houari Boumedienne, Algiers, Algeria. Currently, he is teacher-researcher as a full professor. His research interest on prosody of the speech signal. He is responsible of doctoral formation. He co-authored many paper in international peer-reviewed journal and conferences.