24x7 Service; AnyTime; AnyWhere

Study of noise robustness of First Formant Bandwidth (F1BW) method

Mohd Yusof, Shahrul Azmi and Siraj, Fadzilah and Yaacob, S. and M.P, Paulraj and Nazri, Ahmad (2011) Study of noise robustness of First Formant Bandwidth (F1BW) method. In: 3rd International Conference on Computing and Informatics (ICOCI 2011), 8-9 June 2011, Bandung, Indonesia.

[thumbnail of 99 (1).pdf]
Download (207kB) | Preview


The performance of speech recognition application under adverse noisy condition often becomes the topic of researchers regardless of the language used. Applications that use vowel phonemes require high degree of Standard Malay vowel recognition capability.In Malaysia, researches in vowel recognition is still lacking especially in the usage of Malay vowels, independent speaker systems, recognition robustness and algorithm speed and accuracy. This paper presents a noise robustness study on an improved vowel feature extraction method called First Formant Bandwidth (F1BW) on three classifiers of Multinomial Logistic Regression (MLR), K-Nearest Neighbors (k-NN) and Linear Discriminant Analysis (LDA).Results show that LDA performs best in overall vowel classification compared to MLR and KNN in terms of robustness capability.

Item Type: Conference or Workshop Item (Paper)
Additional Information: ISBN 978-983-2078-49-4 Organized by: UUM College of Arts and Sciences, Universiti Utara Malaysia.
Uncontrolled Keywords: Malay Vowel, Spectrum Envelope, Speech Recognition, Noise Robustness.
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: College of Arts and Sciences
Depositing User: Dr. Shahrul Azmi Mohd. Yusof
Date Deposited: 07 Apr 2015 06:55
Last Modified: 07 Apr 2015 06:55

Actions (login required)

View Item View Item