Dong-geon Kong

Speech enhancement and recognition using circular microphone array for service robots

Speech recognition using circular microphone array is addressed in this paper. Eight microphones are located around the service robot to form a 2D microphone array. To enhance the speech quality, a novel adaptive beamformer composed of a delay-and-sum beamformer, adaptive blocking filters (ABFs) and adaptive cancelling filters (ACFs) is proposed. While the adaptive generalized sidelobe canceller (AGSC) connects the ABF and the ACF in feedforward, the proposed adaptive beamformer has them in feedback. The advantages of the proposed structure are the robustness to the steering vector errors and cross-talks and the reduced number of filter taps that gives the same speech quality compared to the AGSC with a larger number of filter taps. The experimental results show that the proposed structure is superior to the AGSC in objective and subjective evaluations. Speech recognition result shows that the proposed robust adaptive beamformer guarantees the recognition performance even in a low SNR and highly reverberant environment.

Real-time audio-visual localization of user using microphone array and vision camera

In home environments, demands for a robot to serve a user are on the increase, such as cleaning rooms, bringing something to the user, and so on. To achieve these tasks, it is essential for developing a natural way of human-robot interaction (HRI). One of the most natural ways is that the robot approaches the user to do some tasks after recognizing the users call and localizing its position. In this case, user localization becomes a key technology. In this paper, we propose a novel audio visual user localization system. It consists of a microphone array with eight sensors and a video camera. Estimating calling direction is achieved by the spectral subtraction of the spatial spectra. In particular, a novel beam forming method is proposed to suppress the nonstationary audio noises where they always occur in a real world. Furthermore, a robust method for face detection is proposed to double check the user based on an Adaboost classifier. It is improved to reduce the false alarms remarkably through a new postprocessing on face candidates. Successful results in a real home environment show its efficacy and feasibility. The implementation issues, limitations, and their possible solutions are also discussed.

High-quality speech acquisition and recognition system for home-agent robot

A PC-based real-time speech processing system designed for the home-agent robot is presented. The key feature of the proposed system is the speech acquisition module using a microphone array which enables acquiring high-quality speech of a distant talker.

A reliability index of shear wave speed measurement for shear wave elastography

Shear wave elastography is widely used for the noninvasive measurement of tissue stiffness. Assessing liver fibrosis, for example, by measuring shear wave propagation speed is gaining popularity. Elastography data, however, is often contaminated with low SNR and the results become unreliable. Quantification of the reliability of shear wave measurement, therefore, has a significant practical importance. We propose a performance index called “Reliability Measurement Index (RMI)” which is calculated by the weighted sum of two factors: the residual of the wave equation and the magnitude of the shear wave. The residual error accounts for the deviation from the wave equation due to error sources including measurement noises and motion artifacts. Magnitude of induced shear wave is also used to reflect the SNR of the signal. The proposed approach has been successfully implemented on a commercial diagnostic ultrasound system (RS-80A with Prestige, Samsung Medison, Korea). The proposed performance index has been tested in both phantom and in-vivo studies. Initial studies show that high values of RMI are strongly correlated with reproducible measurements. The proposed index can be utilized to filter out unreliable measurements and result in performance improvement of shear wave elastography.

Improved Kanade-Lucas-Tomasi tracker for images with scale changes

To match two images with a large scale difference, a scale parameter can be introduced into the warp parameters of the KLT tracker. For some images, the KLT tracker with the scale warp parameter fails to converge. We assume that this result is caused by the singularity of the Hessian matrix. An improved KLT tracker is proposed to avoid this tracking failure. The proposed method introduces an index (scale invariance index) to determine how close the Hessian matrix is to a singular one with the scale warp parameter. According to the index, either of two different sets of warp parameters is selected: one is with the scale warp parameter and the other is without it.

Noninvasive ultrasound temperature imaging with fusion algorithm

There is a great demand for a noninvasive temperature imaging to commercialize the US guided HIFU system. Echo shift is currently the most technologically developed method, but it cannot give an exact temperature over roughly 43°C since the relation between temperature and speed of sound is irregular depending on the temperature range and tissue type. CBE (Change in Backscattered Energy) has wider temperature range but has the severe artifact that appears behind heated region on ultrasound beam pathway. The object of this paper was to develop a temperature imaging method over the full temperature range by remedying these shortcomings. We present analysis for characteristics of echo shift and CBE up to 60°C through experiments and a fusion approach probabilistically combining echo shift and CBE for more exact temperature imaging over wider temperature range. They can be modeled based on the previous fusion temperature images and the current temperature images by each method. Then the current fusion temperature image can be obtained by combining the two temperature images with optimal weights calculated from the two error covariance maps. The possibility of this method was verified through in-vitro experiments.

Temperature estimation for HIFU therapy using Bioheat Transfer Equation

Noninvasive temperature estimation is important in the field of thermal therapy including High Intensity Focused Ultrasound (HIFU) treatment. Especially, temperature estimation with ultrasound is essential for safe treatment with ultrasound guided HIFU. Ultrasound temperature estimation based on echo-shift is a representative method yet it does not provide accurate estimation over 43 ` C since the relationship between sound speed and temperature is nonlinear. In this paper, a temperature estimation based on echo shift combined with Bioheat Transfer Equation (BHTE) is proposed to overcome the limitation of estimation range in HIFU treatment. In in-vitro experimental results, the proposed method estimates the temperature within O.65`C at the focus.