• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.1
• /
• pp.8-14
• /
• 2002

In this paper, we realized a real-time text-independent speaker recognition system using gaussian mixture model, and applied frame level likelihood normalization method which shows its effects in verification system. The system has three parts as front-end, training, recognition. In front-end part, cepstral mean normalization and silence removal method were applied to consider speaker's speaking variations. In training, gaussian mixture model was used for speaker's acoustic feature modeling, and maximum likelihood estimation was used for GMM parameter optimization. In recognition, likelihood score was calculated with speaker models and test data at frame level. As test sentences, we used text-independent sentences. ETRI 445 and KLE 452 database were used for training and test, and cepstrum coefficient and regressive coefficient were used as feature parameters. The experiment results show that the frame-level likelihood method's recognition result is higher than conventional method's, independently the number of registered speakers.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1993.06a
• /
• pp.121-124
• /
• 1993

This paper is a study on the word recognition using neural network. A limited vocabulary, speaker independent, isolated word recognition system has been built. This system recognizes isolated word without performing segmentation, phoneme identification, or dynamic time wrapping. It needs a static pattern approach to recognize a spatio-temporal pattern. The preprocessing only includes preceding and tailing silence removal, and word length determination. A LPC analysis is performed on each of 24 equally spaced frames. The PARCOR coefficients plus 3 other features from each frame is extracted. In order to simplify a structure of neural network, we composed binary code form to decrease output nodes.

• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.49 no.1
• /
• pp.37-43
• /
• 2000

In this experimental study we proposed the double dielectric barrier discharge (DDBD) reactor to produce as high an electric field as possible. The experiment are conducted for applied voltage from 15 to 20[kV], $1~4[\ell/min]$ of gas flow rate and 120[Hz] and 240[Hz] of pulse rate. Superposition discharge(SPD) generated in DDBD which combined the surface discharge with the silence discharge was the most effective to reduce the $NO_x$. In the decomposition efficiency per watt, the low pulse rate gave better efficiency than the high pulse rate. However in DeNOx rate, the high pulse rate gave better performance than the low pulse rate. $NO_x$ removal rate and efficiency increased with increasing the applied voltage in all reactors.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1999.11a
• /
• pp.169-172
• /
• 1999

In this experimental study we Proposed the double dielectric barrier discharge (DDBD) reactor to produce as high an electric field as possible. The experiment are conducted for applied voltage from 15 to 20[tV], flow gas rage at 2[1/min] and pulse rate at 120[pulses/s] and 240[pulses/s]. SPD connection of DDBD which combine the surface discharge with the silence discharge was most effective to reduce the NOx. In the decomposition efficiency per watt, the low pulse rate gave hotter efficiency than that of the high pulse rate. However in DeNOx rate, the high pulse rate gave better performance than that of the low pulse rate. NOx removal rate increased with increasing the applied voltage in all reactors.