Mohamed Hesham Farouk

Emotion Recognition from Speech

Like ASR, emotion recognition can benefit from the merits of wavelet analysis. Similar methodologies may be followed based on WT similar to that used in speech recognition. Mainly, it is realized in literatures that WP parameters are responsive to emotions. Also, many results prove that wavelet-based features improve emotion recognition.

Megavoltage cone beam computed tomography: Commissioning and evaluation of patient dose.

The improvement in conformal radiotherapy techniques enables us to achieve steep dose gradients around the target which allows the delivery of higher doses to a tumor volume while maintaining the sparing of surrounding normal tissue. One of the reasons for this improvement was the implementation of intensity-modulated radio therapy (IMRT) by using linear accelerators fitted with multi-leaf collimator (MLC), Tomo therapy and Rapid arc. In this situation, verification of patient set-up and evaluation of internal organ motion just prior to radiation delivery become important. To this end, several volumetric image-guided techniques have been developed for patient localization, such as Siemens OPTIVUE/MVCB and MVision megavoltage cone beam CT (MV-CBCT) system. Quality assurance for MV-CBCT is important to insure that the performance of the Electronic portal image device (EPID) and MV-CBCT is suitable for the required treatment accuracy. In this work, the commissioning and clinical implementation of the OPTIVUE/MVCB system was presented. The geometry and gain calibration procedures for the system were described. The image quality characteristics of the OPTIVUE/MVCB system were measured and assessed qualitatively and quantitatively, including the image noise and uniformity, low-contrast resolution, and spatial resolution. The image reconstruction and registration software were evaluated. Dose at isocenter from CBCT and the EPID were evaluated using ionization chamber and thermo-luminescent dosimeters; then compared with that calculated by the treatment planning system (TPS- XiO 4.4). The results showed that there are no offsets greater than 1 mm in the flat panel alignment in the lateral and longitudinal direction over 18 months of the study. The image quality tests showed that the image noise and uniformity were within the acceptable range, and that a 2 cm large object with 1% electron density contrast can be detected with the OPTIVUE/MVCB system with 5 monitor units (MU) protocol. The registration software was accurate within 2 mm in the anterior-posterior, left-right, and superior-inferior directions. The additional dose to the patient from MV-CBCT study set with 5 MU at the isocenter of the treatment plan was 5 cGy. For Electronic portal image device (EPID) verification using two orthogonal images with 2 MU per image the additional dose to the patient was 3.8 cGy. These measured dose values were matched with that calculated by the TPS-XiO, where the calculated doses were 5.2 cGy and 3.9 cGy for MVCT and EPID respectively.

Clustering-Based Topic Identification of Transcribed Arabic Broadcast News

In this research different clustering techniques are applied for grouping transcribed textual documents obtained out of audio streams. Since audio transcripts are normally highly erroneous, it is essential to reduce the negative impact of errors gained at the speech recognition stage. In attempt to overcome some of these errors, different stemming techniques are applied on the transcribed text. The goal of this research is to achieve automatic topic clustering of transcribed speech documents, and investigate the impact of applying stemming techniques in combination with a Chi-square similarity measure on the accuracy of the selected clustering algorithms. The evaluation—using F-Measure—showed that using root-based stemming in combination of spectral clustering technique achieved the highest accuracy.

Speech Production and Perception

The main objective of research in speech processing is directed toward finding techniques for extracting features which, robustly, model a speech signal. Some of these features can be characterized by relatively simple models, while others may require more realistic models in both cases of speech production and perception.0

Wavelets, Wavelet Filters, and Wavelet Transforms

Spectral characteristics of speech are known to be particularly useful in describing a speech signal such that it can be efficiently reconstructed after coding or identified for recognition. The wavelets are considered one of such efficient methods for representing the spectrum of speech signals. Wavelets are used to model both production and perception processes of speech. Wavelet-based features prove a success in a widespread area of practical applications in speech-processing realm.

Steganography, Forensics, and Security of Speech Signal

Wavelet filter banks for perfect reconstruction can help in retrieving a hidden signal. In the wavelet domain, different techniques are applied on the wavelet coefficients to increase the hiding capacity and perceptual transparency. In general, steganography in wavelet domain shows high hiding capacity and transparency.

Clinical Diagnosis and Assessment of Speech Pathology

WT coefficients of normal voice signal have a remarkable difference compared to pathological one. This difference is distributed overall the speech frequency bands with different resolutions. Accordingly, WT is successfully used as a noninvasive method to diagnose vocal pathologies.

Scalogram and Nonlinear Analysis of Speech

As voice source generally interacts with the vocal tract in a nonlinear way, the interaction may take place at the glottis during the periodic vibration of vocal cords. The resulting excitation affects the lower-frequency components of produced voice at lips. Instead, turbulent sound source interacts in a way that influences the higher-frequency components. So, the wavelet decomposition can explore such nonlinear behavior through MRA. Nonlinear and chaotic components of a speech signal can be verified through scalogram analysis obtained from such MRA using CWT. A scale index obtained from CWT can confirm chaotic behavior even for highly periodic waveforms which is the case in speech vowels.

Spectral Analysis of Speech Signal and Pitch Estimation

Wavelet transform (WT) provides a way to explore the spectral characteristics of non-stationary speech signals. Multiresolution analysis based on the wavelet theory permits the introduction of the concepts of signal filtering with different bandwidths or frequency resolutions. As both time and frequency analysis can be conducted by WT, the tree structure of WP analysis can be customized to match the critical bands of human hearing giving better spectral estimation for speech signal than other methods. Wavelet-based pitch estimation assumes that the glottis closures are correlated with the maxima in the adjacent scales of the WT. This approach ensures more accurate estimation of pitch period.

Speech Enhancement and Noise Suppression

Wavelet analysis has been widely used for noise suppression in signals. The multiresolution properties of wavelet analysis reflect the frequency resolution of the human ear. The wavelet transform (WT) can be adapted to distinguish noise in speech through its properties in the time and frequency domains.