Raseeda Hamzah

Acoustical Analysis of Filled Pause in Malay Spontaneous Speech

Filled pause is one of disfluencies types, identified as the often occurred disfluency in spontaneous speech, known to affect Automatic Speech Recognition accuracy. The purpose of this study is to analyze acoustical features of filled pauses in Malay language spontaneous speech as the preliminary step of filled pause detection. The acoustic features that are extracted from the filled pause are formant frequencies and pitch. Two automated segmentation methods which are Zero Crossing Rates and Gaussian Probability Density Function are compared in our study to acquire an exact representation of the filled pause. The results reveal that the pitch and formant frequencies have lower standard deviation when segmented using Gaussian Probability Density Function compared to Zero Crossing Rates. The analysis of Malay filled pause presented in this paper is important as it proved that filled pauses in any language have standard acoustic features such as flat pitch and stable formant frequencies.

Filled Pause Classification Using Energy-Boosted Mel-Frequency Cepstrum Coefficients

Filled pause is one type of disfluency, identified as the often occurred disfluency in spontaneous speech and known to affect Automatic Speech Recognition accuracy. The purpose of this study is to analyze the impact of boosting Mel-Frequency Cepstral Coefficients with energy feature in classifying filled pause. A total of 828 filled pauses comprising a mixture of 62 male and female speakers are classified into /mhm/, /aaa/ and /eer/. A back-propagation neural network using fusion of gradient descent with momentum and adaptive learning rate is used as the classifier. The results revealed that energy-boosted Mel-Frequency Cepstral Coefficients produced a higher accuracy rate of 77 % in classifying filled pauses.

Can Convolution Neural Network (CNN) Triumph in Ear Recognition of Uniform Illumination Invariant

Received Mar 3, 2018 Revised Apr 11, 2018 Accepted Apr 21, 2018 Paintball has gained a huge popularity in Malaysia with growing number of tournaments organized nationwide. Currently, Ideal Pro Event, one of the paintball organizer found difficulties to pair a suitable opponent to against one another in a tournament. This is largely due to the manual matchmaking method that only randomly matches one team with another. Consequently, it is crucial to ensure a balanced tournament bracket where eventual winners and losers not facing one another in the very first round. This study proposes an intelligent matchmaking using Particle Swarm Optimization (PSO) and tournament management system for paintball organizers. PSO is a swarm intelligence algorithm that optimizes problems by gradually improving its current solutions, therefore countenancing the tournament bracket to be continually improved until the best is produced. Indirectly, through the development of the system, it is consider as an intelligence business idea since it able to save time and enhance the company productivity. This algorithm has been tested using 3 size of population; 100, 1000 and 10,000. As a result, the speed of convergence is consistent and has not been affected through big population.N. N. S. Abdul Rahman, N.M. Saad, A. R. Abdullah, M. R. M. Hassan, M. S. S. M. Basir, N. S. M. Noor 1,2,4,6Faculty of Electronic and Computer Engineering, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia 2,3Center for Robotics and Industrial Automation, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia 3,5Faculty of Electrical Engineering, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, MalaysiaLight rail transit (LRT), or fast tram is urban public transport using rolling stock similar to a tramway, but operating at a higher capacity, and often on an exclusive right-of-way. Indonesia as one of developing countries has been developed the LRT in two cities of Indonesia, Palembang and Jakarta. There are opinions toward the development of LRT, negative and positive opinions. To reveal the level of LRT development acceptance, this research uses machine learning approach to analyze the data which is gathered through social media. By conducting this paper, the data is modeled and classified in order to analyze the social sentiment towards the LRT development.Mohamad, S., Nasir, F.M., Sunar, M.S., Isa, K., Hanifa, R.M., Shah, S.M., Ribuan, M.N., Ahmad, A. 1,4,6,7,8Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Johor, Malaysia 1,2,3UTM-IRDA Digital Media Centre, Media and Game Innovation Centre of Excellence, Universiti Teknologi Malaysia, Johor, Malaysia 1,2,3Faculty of Computing, Universiti Teknologi Malaysia, Johor, Malaysia 5Centre for Diploma Studies, Universiti Tun Hussein Onn Malaysia, Johor, Malaysia 6Research Centre for Applied Electromagnetics, Universiti Tun Hussein Onn Malaysia, Johor, MalaysiaReceived Jan 31, 2018 Revised Apr 21, 2018 Accepted Apr 30, 2018 Bluetooth is an emerging mobile ad-hoc network that accredits wireless communication to connect various short range devices. A single hop network called piconet is the basic communication topology of bluetooth which allows only eight active devices for communication among them seven are active slaves controlled by one master. Multiple piconets are interconnected through a common node, known as Relay, to form a massive network called as Scatternet. It is obvious that the performance of Scatternet scheduling is highly dependent and directly proportionate with the performance of the Relay node. In contrary, by reducing the number of Relays, it may lead to poor performance, since every Relay has to perform and support several piconet connections. The primary focus of this study is to observe the performance metrics that affects the inter-piconet scheduling since the Relay node’s role is like switch between multiple piconets. In this paper, we address and analyze the performance issues to be taken into consideration for efficient data flow in Scatternet based on Relay node.

Influences of age in emotion recognition of spontaneous speech: A case of an under-resourced language

Recognizing emotions using natural or spontaneous speech are extremely difficult compared to doing the same for acted or elicited speeches. Speech emotion recognition for real conversation such as spontaneous speech requires linguistic information of the speech to be included in the speech emotion recognition component to achieve a high recognition rate. However, with the lack of digital speech resources of an under-resourced language, this requirement poses a problem. In this paper, speech emotion recognition of spontaneous speech in Malay language using prosodic features and Random Forest classifier is presented. We also investigate the influence of age categorized as children, young adults and middle-aged on emotion recognition. Ninety spontaneous speech sentences from 30 native speakers of Malay language are collected and classified into three emotions, which are happy, angry and sad. Results show that the spontaneous speech of middle-aged group achieved the highest accuracy rate followed by children age group and finally the young adults. While sad emotions are recognized satisfactorily across all age groups, confusions exist between happy and angry emotions.

Impact of acoustical voice activity detection on spontaneous filled pause classification

Filled pause detection is imperative for spontaneous speech recognition as it may degrade speech recognition rate. However, filled pause is commonly confused with elongation as they shared the same acoustical properties. Few attempts of classifying filled pause and elongation employed Hidden Markov model. Our proposed method of utilizing Neural Network as a classifier achieved 96% precision rate. We also proved that voice activity detection (VAD) affects the performance of speech recognition. Three acoustical-based VAD are compared and the best precision rate is achieved by incorporating volume and first-order difference features. Experiments are conducted using Malay language spontaneous speeches of Malaysia Parliamentary Debate sessions.

Nurturing Filled Pause Detection for Spontaneous Speech Retrieval

In this paper we investigate methods to adapt a system for filled pause (FP) disfluency removal to different data properties. A gradient descent algorithm for parameter optimization is presented which achieves 80.6% recall and 87.7% precision on the FP dataset and 46.5% recall and 79.6% precision on the FPElo dataset. This compares to the results produced with hand-optimization on the test set. Furthermore we investigated the impact of cross-validation and training set selection on recognizer output in order to improve the speech retrieval system.

Dynamic Connection Strategies (DyConS) for spoken Malay speech recognition

This paper presents the fusion of artificial intelligence (AI) learning algorithms that are genetic algorithms (GA) and conjugate gradient (CG) methods. Both methods are used to find the optimum weights for the hidden and output layers of feedforward artificial neural network (ANN) model. Each algorithm is presented in separate module and we proposed three different types of Dynamic Connection Strategies (DyConS) for combining both algorithms to improve the recognition performance of spoken Malay speech recognition. Two different GA techniques are used in this research: a mutated GA technique is proposed and compared with the standard GA technique. One hundred experiments with 5000 words are conducted using the proposed DyConS. Owing to previous facts, GA combined with ANN proved to attain certain advantages with sufficient recognition performance. Thus, from the results, it was observed that the performance of mutated GA algorithm when combined with CG is better than standard GA and CG models. Integrating the GA with feed-forward network improved mean square error (MSE) performance and with good connection strategy by this two stage training scheme, the recognition rate is increased up to 99%.