Advertisement

Noise Robustness of Spectrum Delta (SpD) Features in Malay Vowel Recognition

  • Mohd Yusof Shahrul Azmi
  • M. Nor Idayu
  • D. Roshidi
  • A. R. Yaakob
  • Sazali Yaacob
Part of the Communications in Computer and Information Science book series (CCIS, volume 350)

Abstract

In Malaysia, there is increasing number of speech recognition researchers focusing on developing independent speaker speech recognition systems that uses Malay Language which are noise robust and accurate. The performance of speech recognition application under adverse noisy condition often becomes the topic of interest among speech recognition researchers regardless of the languages in use. This paper present a study of noise robust capability of an improved vowel feature extraction method called Spectrum Delta (SpD). The features are extracted from both original data and noise-added data and classified using three classifiers; (i) Multinomial Logistic Regression (MLR), (ii) K-Nearest Neighbors (k-NN) and (iii) Linear Discriminant Analysis (LDA). Results show that the proposed SpD is robust towards noise and LDA performs the best in overall vowel classification compared to MLR and k-NN in terms of robustness capability especially with signal-to-noise (SNR) above 20dB.

Keywords

Malay Vowel Spectrum Envelope Speech Recognition Noise Robustness 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Rosdi, F., Ainon, R.: Isolated malay speech recognition using Hidden Markov Models. In: International Conference on Computer and Communication Engineering (ICCCE 2008), Kuala Lumpur, Malaysia, pp. 721–725 (2008)Google Scholar
  2. 2.
    Devore, S., Shinn-Cunningham, B.G.: Perceptual consequences of including reverbera-tion in spatial auditory displays. In: 2003 International Conference on Auditory Display, Boston, MA, USA, pp. 75–78 (2003)Google Scholar
  3. 3.
    Uhl, C., Lieb, M.: Experiments with an extended adaptive SVD enhancement scheme forspeech recognition in noise. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2001), Salt Lake City, UT, USA, pp. 281–284 (2001)Google Scholar
  4. 4.
    Al-Haddad, S., Samad, S., Hussain, A., Ishak, K.: Isolated Malay Digit Recognition Using Pattern Recognition Fusion of Dynamic Time Warping and Hidden Markov Models. American Journal of Applied Sciences 5, 714–720 (2008)CrossRefGoogle Scholar
  5. 5.
    Huang, X., Acero, A., Hon, H.: Spoken language processing: A guide to theory, algorithm, and system development. Prentice Hall PTR, Upper Saddle River (2001)Google Scholar
  6. 6.
    Kyriakou, C., Bakamidis, S., Dologlou, I., Carayannis, G.: Robust Continuous Speech Recognition in the Presence of Coloured Noise. In: Proceedings of 4th European Conference on Noise Control (EURONOISE 2001), Patra, pp. 702–705 (2001)Google Scholar
  7. 7.
    Shahrul Azmi, M.Y.: Feature Extraction and Classification of Malay Speech Vowels, in School of Mechatronics. Ph.D, Kangar, Perlis. Universiti Malaysia Perlis, Malaysia (UniMAP) (2010) Google Scholar
  8. 8.
    Lim, C.P., Woo, S.C., Loh, A.S., Osman, R.: Speech Recognition Using Artificial Neural Networks. In: 1st International Conference on Web Information Systems Engineering (WISE 2000), Hong Kong, China, pp. 419 (2000)Google Scholar
  9. 9.
    Salam, M., Mohamad, D., Salleh, S.: Neural network speaker dependent isolated Malay speech recognition system: handcrafted vs genetic algorithm. In: 6th International Symposium on Signal Processing and its Applications (ISSPA 2001), Kuala Lumpur, Malaysia (2001)Google Scholar
  10. 10.
    Tan, C., Jantan, A.: Digit Recognition Using Neural Networks. Malaysian Journal of Computer Science 17, 40–54 (2004)Google Scholar
  11. 11.
    Ting, H.N., Mark, K.M.: Speaker-dependent Malay Vowel Recognition for a Child with Articulation Disorder Using Multi-layer Perceptron. In: 4th Kuala Lumpur International Conference on Biomedical Engineering 2008, pp. 238–241 (2008)Google Scholar
  12. 12.
    Yusof, S.A.M., Yaacob, S., Murugesa, P.: Improved Classification of Malaysian Spoken Vowels using Formant Differences. Journal of ICT (JICT) 7 (December 2008)Google Scholar
  13. 13.
    Nazari, M., Sayadiyan, A., Valiollahzadeh, S.M.: Speaker-Independent Vowel Recognition in Persian Speech. In: 3rd International Conference on Information and Communication Technologies: From Theory to Applications (ICTTA 2008), Umayyad Palace, Damascus, Syria, pp. 1–5 (2008)Google Scholar
  14. 14.
    Carvalho, M., Ferreira, A.: Real-Time Recognition of Isolated Vowels. In: André, E., Dybkjær, L., Minker, W., Neumann, H., Pieraccini, R., Weber, M. (eds.) PIT 2008. LNCS (LNAI), vol. 5078, pp. 156–167. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  15. 15.
    Bresolin, A., Neto, A., Alsina, P.: Brazilian Vowels Recognition using a New Hierarchical Decision Structure with Wavelet Packet and SVM (2007)Google Scholar
  16. 16.
    Muralishankar, R., Kaushik, L.N., Ramakrishnan, A.G.: Time-scaling of speech and music using independent subspace analysis. In: International Conference on Signal Processing and Communications (SPCOM 2004), pp. 310–314 (2004)Google Scholar
  17. 17.
    Merkx, P., Miles, J.: Automatic Vowel Classification in Speech, Department of Mathematics, Duke University, Durham, NC, USA, Final Project for Math 196S2005Google Scholar
  18. 18.
    Ting, H., Yunus, J.: Speaker-independent Malay vowel recognition of children using multi-layer perceptron. In: IEEE Region 10 Conference, TENCON 2004 (2004)Google Scholar
  19. 19.
    Al-Haddad, S., Samad, S., Hussain, A., Ishak, K., Noor, A.: Robust Speech Recognition Using Fusion Techniques and Adaptive Filtering. American Journal of Applied Sciences 6, 290–295 (2009)Google Scholar
  20. 20.
    Hawley, M.: Structure out of Sound, in School of Architecture and Planning. PhD, p. 185. Massachusetts Institute of Technology, Massachusetts (1993)Google Scholar
  21. 21.
    Scheirer, E., Slaney, M.: Construction and evaluation of a robust multifeature speech/music discriminator. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 1997), Munich, Germany, pp. 1331–1334 (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Mohd Yusof Shahrul Azmi
    • 1
  • M. Nor Idayu
    • 1
  • D. Roshidi
    • 1
  • A. R. Yaakob
    • 1
  • Sazali Yaacob
    • 2
  1. 1.College of Arts and SciencesUniversiti Utara MalaysiaMalaysia
  2. 2.School of MechatronicsUniversiti Malaysia PerlisMalaysia

Personalised recommendations