Mansour Alsulaiman

Formant analysis in dysphonic patients and automatic Arabic digit speech recognition

Background and objectiveThere has been a growing interest in objective assessment of speech in dysphonic patients for the classification of the type and severity of voice pathologies using automatic speech recognition (ASR). The aim of this work was to study the accuracy of the conventional ASR system (with Mel frequency cepstral coefficients (MFCCs) based front end and hidden Markov model (HMM) based back end) in recognizing the speech characteristics of people with pathological voice.Materials and methodsThe speech samples of 62 dysphonic patients with six different types of voice disorders and 50 normal subjects were analyzed. The Arabic spoken digits were taken as an input. The distribution of the first four formants of the vowel /a/ was extracted to examine deviation of the formants from normal.ResultsThere was 100% recognition accuracy obtained for Arabic digits spoken by normal speakers. However, there was a significant loss of accuracy in the classifications while spoken by voice disordered subjects. Moreover, no significant improvement in ASR performance was achieved after assessing a subset of the individuals with disordered voices who underwent treatment.ConclusionThe results of this study revealed that the current ASR technique is not a reliable tool in recognizing the speech of dysphonic patients.

Environment Recognition Using Selected MPEG-7 Audio Features and Mel-Frequency Cepstral Coefficients

In this paper, we propose a system for environment recognition using selected MPEG-7 audio low level descriptors together with conventional mel-frequency cepstral coefficients (MFCC). The MPEG-7 descriptors are first ranked based on Fisher’s discriminant ratio. Then principal component analysis is applied on top ranked 30 MPEG-7 descriptors to obtain 13 features. These 13 features are appended with MFCC features to complete the feature set of the proposed system. Gaussian mixture models (GMMs) are used as classifier. The system is evaluated using ten different environment sounds. The experimental results show a significant improvement in recognition performance of the proposed system over MFCC or full MPEG-7 descriptor based systems. For example, the best performance is achieved in Restaurant environment where MFCC, full MPEG-7, and the proposed method give 90%, 94%, and 96% accuracy, respectively.

Comparative study of soft computing techniques for mobile robot navigation in an unknown environment

Robot navigation and obstacle avoidance using fuzzy logic controller is presented.Soft computing techniques are used to optimize the performance of fuzzy logic.The automatic tuning was done by using three soft computing techniques: GA, PSO, and NN.The best performance in terms of travelling time and speed is based on GA-Fuzzy.The PSO-Fuzzy and Neuro-Fuzzy methods have better performance in terms of distance travelled. An autonomous mobile robot operating in an unstructured environment must be able to deal with dynamic changes of the environment. Navigation and control of a mobile robot in an unstructured environment are one of the most challenging problems. Fuzzy logic control is a useful tool in the field of navigation of mobile robot. In this research, fuzzy logic controller is optimized by integrating fuzzy logic with other soft computing techniques like genetic algorithm, neural networks, and Particle Swarm Optimization (PSO). Soft computing techniques are used in this work to tune the membership function parameters of fuzzy logic controller to improve the navigation performance. Four methods have been designed and implemented: manually constructed fuzzy logic (M-Fuzzy), fuzzy logic with genetic algorithm (GA-Fuzzy), fuzzy logic with neural network (Neuro-Fuzzy), and fuzzy logic with PSO (PSO-Fuzzy). The performances of these approaches are compared through computer simulations and experiment number of scenarios using Khepera III mobile robot platform. Hybrid fuzzy logic controls with soft computing techniques are found to be most efficient for mobile robot navigation. The GA-Fuzzy technique is found to perform better than the other techniques in most of the test scenarios in terms of travelling time and average speed. The performances of both PSO-Fuzzy and Neuro-Fuzzy are found to be better than the other methods in terms of distance travelled. In terms of bending energy, the PSO-Fuzzy and Neuro-Fuzzy are found to be better in simulation results. Although, the M-Fuzzy is found to be better using real experimental results. Hence, the most important system parameter will dictate which of the four methods to use.

Automatic voice disorder classification using vowel formants

In this paper, we propose an automatic voice disorder classification system using first two formants of vowels. Five types of voice disorder, namely, cyst, GERD, paralysis, polyp and sulcus, are used in the experiments. Spoken Arabic digits from the voice disordered people are recorded for input. First formant and second formant are extracted from the vowels [Fatha] and [Kasra], which are present in Arabic digits. These four features are then used to classify the voice disorder using two types of classification methods: vector quantization (VQ) and neural networks. In the experiments, neural network performs better than VQ. For female and male speakers, the classification rates are 67.86% and 52.5%, respectively, using neural networks. The best classification rate, which is 78.72%, is obtained for female sulcus disorder.

An Investigation of Multidimensional Voice Program Parameters in Three Different Databases for Voice Pathology Detection and Classification

BACKGROUND AND OBJECTIVE Automatic voice-pathology detection and classification systems may help clinicians to detect the existence of any voice pathologies and the type of pathology from which patients suffer in the early stages. The main aim of this paper is to investigate Multidimensional Voice Program (MDVP) parameters to automatically detect and classify the voice pathologies in multiple databases, and then to find out which parameters performed well in these two processes. MATERIALS AND METHODS Samples of the sustained vowel /a/ of normal and pathological voices were extracted from three different databases, which have three voice pathologies in common. The selected databases in this study represent three distinct languages: (1) the Arabic voice pathology database; (2) the Massachusetts Eye and Ear Infirmary database (English database); and (3) the Saarbruecken Voice Database (German database). A computerized speech lab program was used to extract MDVP parameters as features, and an acoustical analysis was performed. The Fisher discrimination ratio was applied to rank the parameters. A t test was performed to highlight any significant differences in the means of the normal and pathological samples. RESULTS The experimental results demonstrate a clear difference in the performance of the MDVP parameters using these databases. The highly ranked parameters also differed from one database to another. The best accuracies were obtained by using the three highest ranked MDVP parameters arranged according to the Fisher discrimination ratio: these accuracies were 99.68%, 88.21%, and 72.53% for the Saarbruecken Voice Database, the Massachusetts Eye and Ear Infirmary database, and the Arabic voice pathology database, respectively.

A Word-Dependent Automatic Arabic Speaker Identification System

Automatic speaker recognition is one of the difficult tasks in the field of computer speech and speaker recognition. Speaker recognition is a biometric process of automatically recognizing who is speaking on the basis of speaker dependent features of the speech signal. Currently, speaker recognition system is an important need for authenticating the personal like other biometrics such as finger prints and retinal scans. Speech based recognition permits both on site and remote access to the user. In this research, speaker identification system is investigated from the speaker recognition problem point of view. It is an important component of a speech-based user interface. The aim of this research is to develop a system that is capable of identifying an individual from a sample of his or her speech. Arabic language is a semitic language that differs from European languages such as English. Our system is based on Arabic speech. We have chosen to work on a word-dependent system using the Arabic isolated word /ns10 as10 cs10 as10 ms10//[unk]/ a single keyword for the test utterance. This choice has been made because the word /ns10 as10 cs10 as10 ms10//[unk]/ is mostly used by the Arabic speakers. Speech features are extracted using MFCC. The HTK is used to implement the speaker identification module with phoneme based HMM. The designed automatic Arabic speaker identification system contains 100 speakers and it achieved 96.25% accuracy for recognizing the correct speaker.

Vocal fold disorder detection based on continuous speech by using MFCC and GMM

Vocal fold voice disorder detection with a sustained vowel is well investigated by research community during recent years. The detection of voice disorder with a sustained vowel is a comparatively easier task than detection with continuous speech. The speech signal remains stationary in case of sustained vowel but it varies over time in continuous time. This is the reason; voice detection by using continuous speech is challenging and demands more investigation. Moreover, detection with continuous speech is more realistic because people use it in their daily conversation but sustained vowel is not used in everyday talks. An accurate voice assessment can provide unique and complementary information for the diagnosis, and can be used in the treatment plan. In this paper, vocal fold disorders, cyst, polyp, nodules, paralysis, and sulcus, are detected using continuous speech. Mel-frequency cepstral coefficients (MFCC) are used with Gaussian mixture model (GMM) to build an automatic detection system capable of differentiating normal and pathological voices. The detection rate of the developed detection system with continuous speech is 91.66%.

Automatic Arabic digit speech recognition and formant analysis for voicing disordered people

In this paper, analysis of speech from voice disordered people is performed from automatic speech recognition (ASR) point of view. Six different types of voicing disorder (pathological voice) are analyzed to show the difficulty of automatically recognizing their corresponding speech. As a case study, Arabic spoken digits are taken as input. The distribution of first four formants of vowel /a/ is extracted to show a significant deviation of formants from the normal speech to disordered speech. Experiment result reveals that current ASR technique is far from reliable performance in case of pathological speech, and thereby we need attention to this.

Investigation of Voice Pathology Detection and Classification on Different Frequency Regions Using Correlation Functions

OBJECTIVES AND BACKGROUND Automatic voice pathology detection and classification systems effectively contribute to the assessment of voice disorders, which helps clinicians to detect the existence of any voice pathologies and the type of pathology from which patients suffer in the early stages. This work concentrates on developing an accurate and robust feature extraction for detecting and classifying voice pathologies by investigating different frequency bands using correlation functions. In this paper, we extracted maximum peak values and their corresponding lag values from each frame of a voiced signal by using correlation functions as features to detect and classify pathological samples. These features are investigated in different frequency bands to see the contribution of each band on the detection and classification processes. MATERIAL AND METHODS Various samples of sustained vowel /a/ of normal and pathological voices were extracted from three different databases: English, German, and Arabic. A support vector machine was used as a classifier. We also performed a t test to investigate the significant differences in mean of normal and pathological samples. RESULTS The best achieved accuracies in both detection and classification were varied depending on the band, the correlation function, and the database. The most contributive bands in both detection and classification were between 1000 and 8000 Hz. In detection, the highest acquired accuracies when using cross-correlation were 99.809%, 90.979%, and 91.168% in the Massachusetts Eye and Ear Infirmary, Saarbruecken Voice Database, and Arabic Voice Pathology Database databases, respectively. However, in classification, the highest acquired accuracies when using cross-correlation were 99.255%, 98.941%, and 95.188% in the three databases, respectively.

A Hierarchical Fuzzy Control Design for Indoor Mobile Robot

This paper presents a motion control for an autonomous robot navigation using fuzzy logic motion control and stereo vision based path-planning module. This requires the capability to maneuver in a complex unknown environment. The mobile robot uses intuitive fuzzy rules and is expected to reach a specific target or follow a prespecified trajectory while moving among unforeseen obstacles. The robots mission depends on the choice of the task. In this paper, behavioral-based control architecture is adopted, and each local navigational task is analyzed in terms of primitive behaviors. Our approach is systematic and original in the sense that some of the fuzzy rules are not triggered in face of critical situations for which the stereo vision camera can intervene to unblock the mobile robot.