Electrical Engineering

This paper addresses the problem of noise robustness of automatic speech recognition (ASR) systems in noisy car environments using a Minimum Mean-Square Error Short-Time Spectral Amplitude Estimator (MMSE-STSA). This was accomplished by the integration of an adaptive time varying Noise Shaping Filter (NSF) with the MMSE-STSA algorithm in order to improve the speech enhancement performance by "whitening" the noisy speech signals. Experiments were conducted using a noisy version of speech signals extracted from the TIMIT database. The proposed NSF-based STSA algorithm is used as a processor of an ASR system in order to evaluate its robustness in severe interfering car noise environments. The HTK Hidden Markov Model Toolkit was used throughout our experiments. Results show that the proposed approach, when included in the front-end of an HTK-based ASR system, outperforms that of the conventional recognition process in severe interfering car noise environments for a wide range of SNRs down to-12 dB using a noisy version of the TIMIT database.

This paper reports an approach that depends on Continuous Hidden Markov Models (CHMMs) to identify Arabic speakers automatically from their voices. The Mel-Frequency Cepstral Coefficients (MFCCs) were selected to describe the speech signal. The general Gaussian density distribution HMM is developed for the CHMM system. Ten Arabic speakers were used to evaluate our proposed CHMM-based engine. The identification rate was found to be 100% during text dependent experiments. However, for the text-independent experiments, the identification rate was found to be 80%.

An algorithm for improving the performance of analysis-bysynthesis (A-by-S) speech coders is presented. It is shown that proper modifications of the A-by-S strategies commonly used to determine the excitation parameters can be devised. In particular, a redefinition of the classical objective function based on the weighted mean squared error criterion may allow a better tracking of the speech signal transients as well as a better alignement of the synthetic pitch pulses. The implementation details of the algorithm are discussed and experimental results are presented.

This paper reports a comparative study between two identification engines to identify speakers automatically from their voices when speaking spontaneously in Arabic. The first engine is based on the continuous hidden Markov models (CHMMs) while the second one is based on the artificial neural networks (ANNs). The Mel frequency cepstral coefficients (MFCCs) were selected to describe the speech signal. The

In this paper, the AM±FM modulation model is applied to speech analysis, synthesis and coding. The AM±FM model represents the speech signal as the sum of formant resonance signals each of which contains amplitude and frequency modulation. Multiband ®ltering and demodulation using the energy separation algorithm are the basic tools used for speech analysis. First, multiband demodulation analysis (MDA) is applied to the problem of fundamental frequency estimation using the average instantaneous frequency as estimates of pitch harmonics. The MDA pitch tracking algorithm is shown to produce smooth and accurate fundamental frequency contours. Next, the AM±FM modulation vocoder is introduced, which represents speech as the sum of resonance signals. A time-varying ®lterbank is used to extract the formant bands and then the energy separation algorithm is used to demodulate the resonance signals into the amplitude envelope and instantaneous frequency signals. Ecient modeling and coding (at 4.8±9.6 kbits/sec) algorithms are proposed for the amplitude envelope and instantaneous frequency of speech resonances. Finally, the perceptual importance of modulations in speech resonances is investigated and it is shown that amplitude modulation patterns are both speaker and phone dependent.

This demonstration involves two-way automatic speechto-speech translation on a consumer off-the-shelf PDA. This work was done as part of the DARPA-funded Babylon project, investigating better speech-to-speech translation systems for communication in the field. The development of the Speechalator software-based translation system required addressing a number of hard issues, including a new language for the team (Egyptian Arabic), close integration on a small device, computational efficiency on a limited platform, and scalable coverage for the domain.

The performance of well-trained speech recognizers using high quality full bandwidth speech data is usually degraded when used in real world environments. In particular, telephone speech recognition is extremely difficult due to the limited bandwidth of transmission channels. In this paper, we concentrate on the telephone recognition of Egyptian Arabic speech using syllables. Arabic spoken digits were described by showing their constructing phonemes, triphones, syllables and words. Speaker-independent hidden markov models (HMMs)-based speech recognition system was designed using Hidden markov model toolkit (HTK). The database used for both training and testing consists from forty-four Egyptian speakers. In clean environment, experiments show that the recognition rate using syllables outperformed the rate obtained using monophones, triphones and words by 2.68%, 1.19% and 1.79% respectively. Also in noisy telephone channel, syllables outperformed the rate obtained using monophones, triphones and words by 2.09%, 1.5% and 0.9% respectively. Comparative experiments have indicated that the use of syllables as acoustic units leads to an improvement in the recognition performance of HMM-based ASR systems in noisy environments. A syllable unit spans a longer time frame, typically three phones, thereby offering a more parsimonious framework for modeling pronunciation variation in spontaneous speech. Moreover, syllable-based recognition has relatively smaller number of used units and runs faster than word-based recognition.

In this paper, a multi-stream paradigm is proposed to improve the performance of automatic speech recognition (ASR) systems in the presence of highly interfering car noise. It was found that combining the classical MFCCs with some auditory-based acoustic distinctive cues and the main formant frequencies of a speech signal using a multi-stream paradigm leads to an improvement in the recognition performance in noisy car environments.

In this paper, we present a comparative study between two identification engines to identify speakers automatically from their voices when speaking spontaneously in Arabic. The first engine is based on the continuous hidden Markov models (CHMMs) while the second one is based on the artificial neural networks (ANNs). The Mel frequency cepstral coefficients (MFCCs) were selected to describe the speech signal. The general Gaussian density distribution HMM was developed for the CHMM-based engine. Elman network was developed for the ANN-based engine. A series of experiments to evaluate both engines have been carried out using a subset of an arabic database. The identification rate was found to be 100% for both engines during text dependent experiments. However, for text-independent experiments, the performance for the CHMM-based engine outperformed that of the ANN-based engine. The identification rates for the CHMM-and the ANN-based engines were found to be 80% and 50%, respectively.

This research investigates the acoustical characteristics<br> of Al-Madinah Holy Mosque. Extensive field measurements were<br> conducted in different locations of Al-Madinah Holy Mosque to<br> characterize its acoustic characteristics. The acoustical characteristics<br> are usually evaluated by the use of objective parameters in unoccupied<br> rooms due to practical considerations. However, under normal<br> conditions, the room occupancy can vary such characteristics due<br> to the effect of the additional sound absorption present in the room<br> or by the change in signal-to-noise ratio. Based on the acoustic<br> measurements carried out in Al-Madinah Holy Mosque with and<br> without occupancy, and the analysis of such measurements, the<br> existence of acoustical deficiencies has been confirmed.

Over the past several years, the primary focus of investigation for speech recognition has been over the telephone or IP network. Recently more and more IP telephony has been extensively used. This paper describes the performance of a speech recognizer on noisy speech transmitted over an H.323 IP telephony network, where the minimum mean-square error log spectra amplitude (MMSE-LSA) method [1,2] is used to reduce the mismatch between training and deployment condition in order to achieve robust speech recognition. In the H.323 network environment, the sources of distortion to the speech are packet loss and additive noise. In this work, we evaluate the impact of packet losses on speech recognition performance first, and then explore the effects of uncorrelated additive noise on the performance. To explore how additive acoustic noise affects the speech recognition performance, seven types of noise sources are selected for use in our experiments. Finally, the experimental results indicate that the MMSE-LSA enhancement method apparently increased robustness for some types of additive noise under certain packet loss rates over the H.323 telephone network.

In this paper, monosyllables are proposed to be used as acoustic units to improve the performance of automatic speech recognition (ASR) systems of Arabic spoken proverbs in noisy environments. To test our proposed approach, a speakerindependent HMM-based speech recognition system was designed using Hidden Markov Model Toolkit (HTK). A series of experiments on noisy speech has been carried out using an Arabic database that consists of fifty-nine Egyptian speakers. The obtained results show that the recognition rate using monosyllables outperformed the rate obtained using trisyllables by 24.76 % in the noisy environment. Also, we show in this paper that the integration of a pre-processing enhancement technique in the front-end of the monosyllable-based ASR engine leads to an improvement of the recognition rate by 30.8 % compared to the rates obtained using trisyllable-based ASR.

Chapters (4 to 6) and chapters 8) -study the static (time-invariant) EM fields  Electrostatic = ( , , ) and magnetostatic = ( , , ) are independent of each other.  Electrostatic = ( , , ) are produced by static electric charges  Magnetostatic = ( , , ) are produced by uniform motion of electric charges  = ( , , ) and = ( , , )

A new algorithm is presented for the design of fixed point finite impulse response (FIR) digital filters that can be realized using a minimal number of adders while satisfying both the desired hardware implementation constraints and the frequency domain design constraints. The proposed algorithm makes use of a two-stage search method with a new soft-switching optimization criterion, minimizing the Chebyshev error norm in a discrete sanonic signed digit (CSD) space. The proposed design method is implemented as a Matlab-based software package (CSDFIR) that allows the design of both Chebyshev optimal floating point and fixed point CSD FIR filters.