-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, a variable threshold voice activity detector (VAD) is developed to control the operation of a two-sensor adaptive noise canceller (ANC). The VAD prohibits the reference input of the ANC from containing some strength of actual speech signal during adaptation periods. The novelty of this approach resides in using the residual output from the noise canceller to control the decisions made by the VAD. Thresholds of full-band energy and zero-crossing features are adjusted according to the residual output of the adaptive filter. Performance evaluation of the proposed approach is quoted in terms of signal to noise ratio improvements as well mean square error (MSE) convergence of the ANC. The new approach showed an improved noise cancellation performance when tested under several types of environmental noise. Furthermore, the computational power of the adaptive process is reduced since the output of the adaptive filter is efficiently calculated only during non-speech periods.
Sensors 01/2012; 12(5):6727-45. · 1.74 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: X-ray radiograph images are used usually for vertebral diseases detection and fractures that can be visible on lateral view. In general the x-ray images are poor quality images with low contrast and they do not provide momentous information concerning pathologies that are of interest to the medical researchers in terms of texture or colour. Consequently the enhancement may have a critical role in affording plenty and satisfactory visual information to the radiologist and clinician. In this paper, we propose a new approach for noise reduction in the cervical and lumbar radiograph images by employing a non-linear contrast adjustment scheme based adaptive factor. To achieve this main objective, firstly we investigate the use of non-linear gamma correction filter with variable gain factor value and draw an end conclusion of its effect to the quantum noise reduction in the spine radiographs images, secondly a new algorithm for adaptive gain factor detection was developed based on statistical pixel-level (SPL) features extraction and traditionally artificial neural networks (ANN's) model as a classifier to find "best" gain factor. Thirdly, experimental results are presented to examine and evaluate the filter performance, this evaluation done via visual interpretation and quantitative measurement by measuring the MSE and PSNR between the input and the resulting filtered images using gamma correction with adaptive gain factor versus different gain factor value.
Scientific research and essays 10/2011; 620:4246-4258. · 0.32 Impact Factor
-
09/2011; , ISBN: 978-953-307-158-9
-
[show abstract]
[hide abstract]
ABSTRACT: Performances of speaker verification systems are superb in clean noise-free conditions but the reliability of the systems
drop severely in noisy environments. In this study, we propose a novel approach by introducing Support Vector Machine (SVM)
as indicator system for audio reliability estimation. This approach directly validate the quality of the incoming (claimant)
speech signal so as to adaptively change the weighting factor for fusion of both subsystem scores. The effectiveness of this
approach has been experimented to a multibiometric verification system that employs lipreading images as visual features.
This verification system uses SVM as a classifier for both subsystems. Principle Component Analysis (PCA) technique is executed
for visual features extraction while for the audio feature extraction; Linear Predictive Coding (LPC) technique has been utilized.
In this study, we found that the SVM indicator system is able to determine the quality of the speech signal up to 99.66%.
At 10 dB SNR, EER performances are observed as 51.13%, 9.3%, and 0.27% for audio only system, fixed weighting system and adaptive
weighting system, respectively.
KeywordsBiometric verification system-reliability estimation-support vector machine
04/2010: pages 165-177;
-
[show abstract]
[hide abstract]
ABSTRACT: In this study, we propose a novel approach for speaker verification system that uses a spectrogram image as features and Unconstrained Minimum Average Correlation Energy (UMACE) filters as classifiers. Since speech signal is a behavioral signal, the speech data has a tendency not to consistently reproduce due to the change of speaking rates, health, emotional conditions, temperature and humidity. In order to overcome this problem, a modification of UMACE filters architecture is proposed by executing a multi-sample fusion using speech and lipreading data. So as to evaluate the outstanding fusion scheme, five multisample fusion strategies, i.e. maximum, minimum, median, average and majority vote are first experimented using thespeech signal data. Afterward, the performance of the audiovisualsystem using the enhanced UMACE filters is then tested. Here, lipreading data is combined to the audio samples pool and the outstanding fusion scheme that found in prior experiment is used as multi-sample fusion scheme. The Digit Database had been used for performance evaluation and the performance up to 99.64% is achieved by using the enhanced UMACE filters for the speech only system which is 6.89% improvement compared with the base line approach. Subsequently, the implementation of the audio-visual system is observed to be significant in order to broaden the PSR score interval between the authentic and imposter data as well as to further improve the performance of audio only system that offer toward a robust verification system.
International Journal on Computer Science and Engineering. 01/2010;
-
10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010, Kuala Lumpur, Malaysia, 10-13 May, 2010; 01/2010
-
[show abstract]
[hide abstract]
ABSTRACT: Kaedah pembelajaran koperatif (KOOP) berpusatkan pelajar merupakan suatu metodologi pengajaran aktif dalam kumpulan-kumpulan kecil berbanding kaedah pembelajaran kompetitif (KOMP) atau secara individu dan berpusatkan pensyarah. Teknik Jigsaw yangmerupakan subset pembelajaran KOOP telah menunjukkan keupayaan memupuk kemahiran interaksi berkumpulan, berfikiran kritis serta sifat positif, selaras dengan paradigma masa kini yang berlandas keperluan hasil pembelajaran. Dalam kajian ini ia digunakan dalam proses mengulangkaji topik yang telah diajar di bilik kuliah. Sehubungan dengan itu, kertaskerja ini membincangkan kedua-dua metodologi pembelajaran yang telah dilaksanakan dalam kelas kursus isyarat dan sistem (KL2093) di Fakulti Kejuruteraan, UKM dan mengupas keberkesanannya secara kuantitatif dan kualitatif. Iajuga membandingkan struktur pembelajaran kooperatif dan kompetitif menggunakan rekabentuk kuasi-ujikaji. Analisis kuantitatif dilakukan ke atas dua set data markah peperiksaan pelajar untuk melihat kesan ke atas pencapaian akademik manakala analisis kualitatif dilakukan secara analisis sebab-akibat (cause-effect) untuk mengkaji kesannyaterhadap sikap pelajar. Pemerhatian dan analisis awal menunjukkan teknik jigsaw yang berpusatkan pelajar memberikan kesan yang lebih positif berbanding kaedah tradisional pembelajaran KOMP berpusat pensyarah.The student oriented cooperative leaning method (COOP) exhibit an active teaching methodology in small groups, as compared to the lecturer oriented competitive learning method (COMP). The Jigsaw technique is a subset of the COOP learning that has been demonstrated to nurture good group interaction skill, critical thinking ability, and positive attitude among students that are in agreement with the current outcome based paradigm. In this study, both methods were used in the revision process to reinforce theunderstanding of the topics taught in the class. This paper specifically discusses both methodologies that have been implemented in Signal and System course (KL2093) at the Engineering Faculty, UKM and analyzes its quantitative and qualitative effectiveness. Italso compares the cooperative and competitive structure using the quasi-experiment design approach. The quantitative analysis was carried out on two data sets of examination scores to evaluate their effects towards academic achievements, while, the qualitative analysis based on cause-effect process is performed to investigate the effects towards students’ behavior. Preliminary observation and analysis indicates that the student oriented jigsaw technique is more effective compared to the traditional lecturer oriented COMP learning.
ASEAN Journal of Teaching & Learning in Higher Education. 01/2010;
-
Computational Intelligence in Security for Information Systems 2010 - Proceedings of the 3rd International Conference on Computational Intelligence in Security for Information Systems (CISIS'10), León, Spain, November 11-12, 2010; 01/2010
-
IAENG International Journal of Computer Science. 01/2009;
-
[show abstract]
[hide abstract]
ABSTRACT: Problem statement: Electroencepharogram (EEG) is an extremely complex signal with very low signal to noise ratio and these attributed to difficulty in analyzing the signal. Hence for detecting abnormal segment, a distinctive method is required to train the technologist to distinguish the anomalous in EEG data. The objective of this study was to create a framework to analyze EEG signals recorded from epileptic patients by evaluating the potential of UMACE filter to detect changes in single-channel EEG data during routine epilepsy monitoring. Approach: Normally, the peak to side lobe ratio (PSR) of a UMACE filter was employed as an indicator if a test data is similar to an authentic class or vice versa, however in this study, the consistent changes of the correlation output known as Region Of Interest (ROI) was plotted and monitored. Based on this approach, a novel method to analyze and distinguish variances in scalp EEG as well as comparing both normal and abnormal regions of the patient’s EEG was assessed. The performance of the novelty detection was examined based on the onset and end time of each seizure in the ROI plot. Results: Results showed that using ROI plot of variances one can distinguish irregularities in the EEG data. The advantage of the proposed technique was that it did not require large amount of data for training. Conclusion: As such, it was feasible to perform seizure analysis as well as localizing seizure onsets. In short, the technique can be used as a guideline for faster diagnosis in a lengthy EEG recording.
Journal of Computer Science. 01/2009;
-
ICINCO 2009, Proceedings of the 6th International Conference on Informatics in Control, Automation and Robotics - Signal Processing, Systems Modeling and Control, Milan, Italy, July 2-5, 2009; 01/2009
-
Visual Informatics: Bridging Research and Practice, First International Visual Informatics Conference, IVIC 2009, Kuala Lumpur, Malaysia, November 11-13, 2009, Proceedings; 01/2009
-
Lecture Notes in Engineering and Computer Science. 01/2009;
-
[show abstract]
[hide abstract]
ABSTRACT: This research describes the pitch and timbre determination of the angklung, a musical instrument made entirely out of bamboo. An angklung has two main parts: the frame and the rattle tubes. The pitch of the rattle tubes can be determined using a formula that takes into consideration the length and diameter of the air resonator. This is compared with the results obtained using sound analysis with the fast Fourier transform as well as with measured results. The coupling effects of having two rattles on the pitch and timbre are investigated. It is found that the pitch of the angklung is closely related to the fundamental frequency of air resonance in the bamboo tubes of the angklung rattles. Therefore, the pitch of an angklung can be estimated by calculating that fundamental frequency using information from the length and diameter of the closed cylinder air column of each rattle. The timbre of the angklung is also determined to be a mix of the sound output from each of its individual rattles. The timbre has an identifying characteristic of having two prominent peaks with each one corresponding to the pitch of each rattle.
American Journal of Applied Sciences. 01/2009;
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, we present a speaker verification system based on the Hidden Markov Model (HMM) technique and Recursive Least Squares (RLS) adaptive filtering. The aim of using RLS adaptive filtering is to improve the HMM performance in noisy environments. A Malay spoken digit database is used for the testing and validation modules. It is shown that, in a clean environment a total success rate (TSR) of 89.97% is achieved using HMM. For speaker verification, the true speaker rejection rate is 25.3% while the impostor acceptance rate is 9.99% and the equal error rate (EER) is 16.66%. In noisy environments without RLS adaptive filtering TSRs of between 43.07%–51.26% are achieved for SNRs of 0–30 dBs. Meanwhile, after RLS filtering, TSRs of between 50.95%–56.75% are achieved for SNRs 0–30 dB.
Information Technology, 2008. ITSim 2008. International Symposium on; 09/2008
-
[show abstract]
[hide abstract]
ABSTRACT: Robustness is a key issue in speech recognition. This paper proposes a speech recognition algorithm for Malay digits from 0 to 9. This paper also proposes an algorithm for noise cancellation by using recursive least squares (RLS). This system consists of speech processing inclusive of digit margin and recognition which uses zero crossing and energy calculations. Mel-Frequency Cepstral Coefficient (MFCC) vectors are used to provide an estimate of the vocal tract filter. Meanwhile dynamic time warping (DTW) is used to detect the nearest recorded voice with appropriate global constraint. The global constraint is used to set a valid search region because the variation of the speech rate of the speaker is considered to be limited in a reasonable range, which means that it can prune the unreasonable search space. The algorithm is tested on speech samples that are recorded as a part of a Malay corpus. The results show that the algorithm can recognize almost 80.5% of the Malay digits for all recorded words. By adding RLS noise canceller in the preprocessing stage it increases the accuracy to 92.3%.
Information Technology, 2008. ITSim 2008. International Symposium on; 09/2008
-
Proceedings of the International Workshop on Computational Intelligence in Security for Information Systems, CISIS'08, Genova, Italy, October 23-24, 2008; 01/2008
-
[show abstract]
[hide abstract]
ABSTRACT: Visual speech information, for example the appearance and the movement of lip during speech utterance can characterize a person`s identity and therefore it can be used in personal authentication systems. In this study, we propose a novel approach by using lipreading data i.e., the sequence of entire region of mouth area produced during speech and the implementation of the Unconstrained Minimum Average Correlation Energy (UMACE) filter as a classifier for biometric authentication. The system performance is also enhanced by the implementation of multi sample fusion scheme using average operator. The results obtained from using a Digit Database shows that the use of lipreading information and UMACE filter has good potentials and is highly effective in reducing false acceptance and false rejection rates for speaker verification system performance.
Journal of Applied Sciences. 01/2008;
-
[show abstract]
[hide abstract]
ABSTRACT: This study affords the method of using advance correlation filters in human posture recognition task. Two types of correlation filters were implemented and their efficacy evaluated. The correlation filters under consideration are Minimum Average Correlation Energy (MACE) and Unconstrained Minimum Average Correlation Energy (UMACE). Initial results prove that correlation filters offer significant potential used in posture recognition task with UMACE outperforming the MACE filter. In this research, both filters were subjected to a challenging task to recognize human posture without any restriction on the gender, clothing and posture variations. The UMACE filter performs remarkably well with an average accuracy of 89% compared to MACE filter which attained 42%.
Journal of Applied Sciences. 01/2007;
-
Knowledge-Based Intelligent Information and Engineering Systems, 11th International Conference, KES 2007, XVII Italian Workshop on Neural Networks, Vietri sul Mare, Italy, September 12-14, 2007. Proceedings, Part I; 01/2007
