Since the introduction of hands-free phone set and teleconferencing system, acoustic echo cancellation has been a challenge for engineers. Recently many researches have shown that the best solution for the acoustic echo compensation problem is represented by an adaptive filter which iteratively tries to identify the unknown impulse response of the system from loudspeaker to microphone. In this paper, we apply the delayless subband adaptive filters and fast affine projection algorithm for the identification of room impulse response. Simulation results show 3∼8 dB more enhanced performance than conventional fullband adaptive filters or subband adaptive filters. In addition, fast affine projection algorithm shows better convergence speed at the expense of the low computational complexity than conventional LMS algorithm.

Application of the Filtered-X LMS adaptive filter to active noise cancellation requires to estimate the transfer characteristics between the output and the error signal of the adaptive canceler. In this paper, we derive an adaptive cancellation algorithm and analyze is convergence behavior when the acoustic noise is assumed to consist of multiple sinusoids. The results of the convergence analysis of the Filtered-X LMS algorithm indicate that the effects of parameter estimation inaccuracy on the convergence behavior of the algorithm are characterize by two distinct components : Phase estimation error and estimated magnitude. In particular, the convergence of the Filtered-X LMS algorithm is show to be strongly affected by the accuracy of the phase response estimate. Simulation results of the algorithm are presented which support the theoretical convergence analysis.

This paper attempts to examine the characteristics of underwater acoustic signals distorted in shallow water environments. Time signals are simulated using an acoustic model that employs the Fourier synthesis scheme. An acoustic experiment was conducted in the shallow sea near Pohang, Korea, where water depth is about 60m. The environment in the simulation is set up so that it approximates the experimental condition, which can be regarded as range-independent. The signal is LFM(linar frequency modulated) type centered on one of the four frequencies 200, 400, 600 and 800Hz, each being swept up or down with the bandwidth of 100Hz. To analyze the signal characteristics, the study introduces a spectrum estimation scheme, pseudo Wigner-Ville distribution (PWVD). The simulated and measured signals suffer great interference by the interaction of neighboring rays. Although there are constructive or destructive interference, the signals keep LFM characteristics well. This is thought that only a few dominant rays of small loss contribute to the receive signals in a shallow water environment.

In this paper, we compose neural network predictive HMM(NNPHMM) to provide the dynamic feature of the speech pattern for the HMM. The NNPHMM is the hybrid network of neura network and the HMM. The NNPHMM trained to predict the future vector, varies each time. It is used instead of the mean vector in the HMM. In the experiment, we compared the recognition abilities of the one hundred Korean syllables according to the variation of hidden layer, state number and prediction orders of the NNPHMM. The hidden layer of NNPHMM increased from 10 dimensions to 30 dimensions, the state number increased from 4 to 6 and the prediction orders increased from 10 dimensions to 30 dimension, the state number increased from 4 to 6 and the prediction orders increased from the second oder to the fourth order. The NNPHMM in the experiment is composed of multi-layer perceptron with one hidden layer and CMHMM. As a result of the experiment, the case of prediction order is the second, the average recognition rate increased 3.5% when the state number is changed from 4 to 5. The case of prediction order is the third, the recognition rate increased 4.0%, and the case of prediction order is fourth, the recognition rate increased 3.2%. But the recognition rate decreased when the state number is changed from 5 to 6.

This paper proposes a feature extraction method using wavelet transform for speech recognition. Speech recognition system generally carries out the recognition task based on speech features which are usually obtained via time-frequency representations such as Short-Time Fourier Transform (STFT) and Linear Predictive Coding(LPC). In some respects these methods may not be suitable for representing highly complex speech characteristics. They map the speech features with same may not frequency resolutions at all frequencies. Wavelet transform overcomes some of these limitations. Wavelet transform captures signal with fine time resolutions at high frequencies and fine frequency resolutions at low frequencies, which may present a significant advantage when analyzing highly localized speech events. Based on this motivation, this paper investigates the effectiveness of wavelet transform for feature extraction of wavelet transform for feature extraction focused on enhancing speech recognition. The proposed method is implemented using Sampled Continuous Wavelet Transform (SCWT) and its performance is tested on a speaker-independent isolated word recognizer that discerns 50 Korean words. In particular, the effect of mother wavelet employed and number of voices per octave on the performance of proposed method is investigated. Also the influence on the size of mother wavelet on the performance of proposed method is discussed. Throughout the experiments, the performance of proposed method is discussed. Throughout the experiments, the performance of proposed method is compared with the most prevalent conventional method, MFCC (Mel0frequency Cepstral Coefficient). The experiments show that the recognition performance of the proposed method is better than that of MFCC. But the improvement is marginal while, due to the dimensionality increase, the computational loads of proposed method is substantially greater than that of MFCC.

In this paper, we propose a remote speech input device, a new method of user-friendly speech input in spontaneous speech recognition system. We focus the user friendliness on hands-free and microphone independence in speech recognition applications. Our method adopts two algorithms, the automatic speech detection and the microphone array delay-and-sum beamforming (DSBF)-based speech enhancement. The automatic speech detection algorithm is composed of two stages; the detection of speech and nonspeech using the pitch information for the detected speech portion candidate. The DSBF algorithm adopts the time domain cross-correlation method as its time delay estimation. In the performance evaluation, the speech detection algorithm shows within-200 ms start point accuracy of 93%, 99% under 15dB, 20dB, and 25dB signal-to-noise ratio (SNR) environments, respectively and those for the end point are 72%, 89%, and 93% for the corresponding environments, respectively. The classification of speech and nonspeech for the start point detected region of input signal is performed by the pitch information-base method. The percentages of correct classification for speech and nonspeech input are 99% and 90%, respectively. The eight microphone array-based speech enhancement using the DSBF algorithm shows the maximum SNR gaing of 6dB over a single microphone and the error reductin of more than 15% in the spontaneous speech recognition domain.

An analysis of dynamic responses is carried out on monoclinic anisotropic system due to a buried harmonic line source. The load is in the form of a normal stress acting along an arbitrary axis on the plane of symmetry within the orthotropic materials: In case that the line load is acting along the symmetry axis normal to the plane of symmetry, plane wave equation is coupled with verital shear wave and longitudinal wave. However, if the line load is acting along an arbitrary axis normal to the plane of symmetry, plane wave equation is coupled with vertical shear wave, longitudinal wave and horizontal shear wave. We first considered the equation of motion in a reference coordinate system, where the line load is coincident with a symmetry axis of the orthotropic material. Then the equation of motion is transformed into one with respect to general coordinate system with azimuthal angle by using transformation tensor. Plane wave solutions of monoclinic systems are derived for infinite media. Finally complete solutions for the plane harmonic wave are obtained by calculating the inverse of the integral transforms, in which bulk wave poles are avoided by deforming the contour of the integration to the complex plane. Numerical results for examples of orthotropic material belonging to monoclinic symmetry are demonstrated.

In this paper, we study the response of several anisotropic systems to buried transient line loads. The problem is mathematically formulated based on the equations of motion in the constitutive relations. The load is in form of a normal stress acting with arbitrary axis on the plane of monoclinic symmetry. Plane wave equation is coupled with vertical shear wave, longitudinal wave and horizontal shear wave. We first considered the equation of motion in reference coordinate system, where the line load is coincident with symmetry axis of the orthotrioic material. Then the equation of motion is transformed with respect to general coordiante system with azimuthal angle by using transformation tensor. The load is first described as a body force in the equations of the motion for the infinite media and then it is mathematically characterized. Subsequently the results for semi-infinite spaces is also obtained by using superposition of the infinite medium solution together with a scattered solution from the free surface. Consequently explicit solutions for the displacements are obtained by using Cargniard-DeHoop contour. Numerical results which are drawn from concrete examples of orthotropic material belonging to monoclinic symmetry are demonstrated.