Noise Robustness of First Formant Bandwidth (F1BW) Features in Malay Vowel Recognition

Authors

  • Shahrul Azmi Mohd Yusuf School of Computing, UUM College of Arts and Sciences, Universiti Utara Malaysia, Malaysia
  • Nor Idayu Mahat School of Computing, UUM College of Arts and Sciences, Universiti Utara Malaysia, Malaysia
  • Fadzilah Siraj School of Computing, UUM College of Arts and Sciences, Universiti Utara Malaysia, Malaysia
  • Sazali Yaacob Universiti Malaysia Perlis, Malaysia

DOI:

https://doi.org/10.32890/jict2012.11.9

Keywords:

Malay vowels, spectrum envelope, speech recognition, noise robustness

Abstract

Applications that use vowel phonemes require a high degree of vowel recognition capability. The performance of speech recognition application under adverse noisy conditions often becomes the topic of interest among speech recognition researchers regardless of the languages in use. In Malaysia, there are an increasing number of speech recognition researchers focusing on developing independent speaker speech recognition systems that use the Malay language which is noise robust and accurate. This paper present a study of noise robust capability of an improved vowel feature extraction method called First Formant Bandwidth (F1BW). 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 Linear Discriminant Analysis (LDA). The results show that the proposed F1BW 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.

 

References

Al-Haddad, S., Samad, S., Hussain, A., & Ishak, K. (2008). Isolated Malay digit recognition using pattern recognition fusion of Dynamic Time Warping and Hidden Markov Models. American Journal of Applied Sciences, 5(6), 714-720. Journal of ICT, 11, pp: 147-

Al-Haddad, S., Samad, S., Hussain, A., Ishak, K., & Noor, A. (2009). Robust speech recognition using fusion techniques and adaptive filtering. American Journal of Applied Sciences, 6(2), 290-295.

Bresolin, A., Neto, A., & Alsina, P. (2007). Brazilian vowels recognition using a New Hierarchical Decision Structure with Wavelet Packet and SVM. rlson, R., & Glass, J. (1992). Vowel classification based on analysis-by-synthesis. Paper presented at the 2nd International Conference on - Spoken Language Processing (ICSLP 92).

Carvalho, M., & Ferreira, A. (2008). Real-time recognition of isolated vowels. Paper presented at the Proceedings of the 4th IEEE tutorial and research workshop on Perception and Interactive Technologies for Speech-Based D Systems: Perception in Multimodal Dialogue Systems.

Dy rere S., & Shinn-Cunningham, B. G. (2003, 6-9 July). Perceptual consequences of including reverberation in spatial auditory displays. - 2003 International Conference on Auditory Display, Boston, MA, USA. yan G. (1970). Acoustic theory of speech production. Mouton De Gruyter.

Jiajic, B., & Paliwal, K. K. (2006). Robust speech recognition in noisy. environments based on subband spectral centroid histograms. Audio, J Speech, and Language Processing, IEEE Transactions on, 14(2), 600-O 608. a — 2 llenbrand, J., & Houde, R. (2003). A narrow band pattern-matching model — of vowel perception. The Journal of the Acoustical Society of America, 8. 113, 1044-1055. eine. X., Acero, A., & Hon, H. (2001). Spoken language processing: A guide to theory, algorithm, and system development. Upper Saddle River, NJ, c USA: Prentice Hall PTR.

Kyriakou, C., Bakamidis, S., Dologlou, I., & Carayannis, G. (2001, January. Robust continuous speech recognition in the presence of coloured noise. Proceedings of 4th European Conference on Noise Control (EURONOISE2001), Patra.

Lim, C. P., Woo, S. C., Loh, A. S., & Osman, R. (2000). Speech recognition using artificial neural networks. st International Conference on Web Information Systems Engineering (WISE’00), Hong Kong China. Journal of ICT, 11, pp: 147-

Liu, H., & Ng, M. L. (2009). Formant characteristics of vowels produced by Mandarin esophageal speakers. Journal of Voice, 23(2), 255-260.

Luo, X., Soon, Y., & Yeo, C. K. (2008). An auditory model for robust speech recognition. International Conference on Audio, Language and Image Processing, 2008 (ICALIP 2008)

Shanghai. werk, P., & Miles, J. (2005). Automatic vowel classification in speech (Final Project for Math 196S). Durham, NC, USA: Department of - Mathematics, Duke University. * Muralishankar, R., & O' Shaughnessy, D. (2005). Subspace-based speaker-5 independent vowel recognition. IEEE International Conference on D Acoustics, Speech, and Signal Processing (ICASSP 05) Philadelphia, PA, USA. a Nazari, M., Sayadiyan, A., & Valiollahzadeh, S. M. (2008). Speaker-independent vowel recognition in Persian speech. 3rd International - Conference on Information and Communication Technologies: From - Theory to Applications (ICTTA 08) Umayyad Palace, Damascus, Syria..

Peterson, G., & Barney, H. (1952). Control methods used in a study of the vowels. Journal of the Acoustical Society of America, 24(2), 175-184.

O Rajnoha, J., & Pollak, P. (2007). Modified feature extraction methods in robust speech recognition. 17th International Conference of Radioelektronika, a — 2007, Brno. — Rosdi, EF, & Ainon, R. (2008). Isolated Malay speech recognition using Hidden Markov Models. International Conference on Computer and Q. Communication Engineering (ICCCE 08), Kuala Lumpur, Malaysia. — —_— Salam, M., Mohamad, D., & Salleh, S. (2001). Neural network speaker dependent isolated Malay speech recognition system: Handcrafted vs genetic algorithm. 6th International Symposium on Signal Processing and its Applications (ISSPA2001). Kuala Lumpur, Malaysia.

Shahrul Azmi, M. Y., Siraj, F., Yaacob, S., Paulraj, M. P., & Nazri, A. (2010). Improved Malay vowel feature extraction method based on first and second formants. 2nd International Conference on Computational

Intelligence, Modelling and Simulation (CIMSIM 2011). Bali, Indonesia. Journal of ICT, 11, pp: 147-

Tan, C., & Jantan, A. (2004). Digit recognition using neural networks. Malaysian Journal of Computer Science, 17(2), 40-54.

Ting, H., & Yunus, J. (2004). Speaker-independent Malay vowel recognition of children using multi-layer perceptron. EEE Region 10 Conference (TENCON 2004).

SH. H. N., & Mark, K. M. (2008). 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). ni. C., & Lieb, M. (2001). Experiments with an extended adaptive SVD DO enhancement scheme forspeech recognition in noise. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 01). ®O Salt Lake City, UT, USA. a uckovic, V.,& Stankovic, M.(2001). Formant analysis andvowel classification c methods. 5th International Conference on Telecommunications in Modern Satellite, Cable and Broadcasting Service (TELSIKS 2001).

Sy H. (1977). Normalization of vowels by vocal-tract length and its application to vowel identification. EEE Transactions on Acoustics,... < Speech and Signal Processing, 25(2), 183-192. a) Pp & i

Onn. Q., & Vaseghi, S. (2003). Analysis, modelling and synthesis of formants 2 of British, American and Australian accents. IEEE International — Conference on Acoustics, Speech and Signal Processing (ICASSP — 2003). a a

Qdgeaneh, H., Ahadi, S. M., & Ziaei, A. (2008). A new MFCC improvement PP) method for robust ASR. 9th International Conference on Signal — Processing (ICSP 2008) Beijing, China. ‘sot S. A. M., Yaacob, S., & Murugesa, P. (2008). Improved classification of Malaysian spoken vowels using formant differences. Journal of ICT (JICT), 7, Universiti Utara Malaysia.

Zahorian, S., Nossair, Z., & Norton II, C. (1999). A partitioned neural network approach for vowel classification using smoothed time/frequency features. IEEE Transactions on Speech and Audio Processing, 7(4), 414-425.

Downloads

Published

30-04-2012

Issue

Vol. 11 (2012): Journal of Information and Communication Technology (JICT) Vol. 11, 2012

Section

Articles

How to Cite

Mohd Yusuf, S. A., Mahat, N. I., Siraj, F., & Yaacob, S. (2012). Noise Robustness of First Formant Bandwidth (F1BW) Features in Malay Vowel Recognition. Journal of Information and Communication Technology, 11, 147-162. https://doi.org/10.32890/jict2012.11.9

Research impact

Harvested 2026-09-06
0 citations recorded so far

Counts differ between services because each indexes a different body of literature. None of them is the whole picture.

Identifiers DOI 10.32890/jict2012.11.9

Most read articles by the same author(s)