• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.16 no.5 s.110
• /
• pp.544-550
• /
• 2006

The interaction between people and sound and the way how people consciously perceive their environment are central approach to soundscape research. In this respect, this paper aims to clarify the relationship between water-sound level and recognition region in urban area. As a passive soundscape facility, fountain is a useful way to give place such as public square, park identity and vitality. In this study, to know the optimistic distance and sound level range from fountain, sound levels due to distance were measured and subject responses were checked by questionnaire. As a result, levels from 63 dB to 67 dB were recommended by subjects and moving forward to fountain less satisfactory than backward. Moving forward 5 m and backward 5 m(total range 10 m): there was a difference in satisfaction ratio by 2,5 out of 10. The results of this study could be used for street furniture location design and P.A. system output level.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1820-1825
• /
• 2004

In this paper, we propose a humanoid active audition system which detects the direction of sound and performs speech recognition using just three microphones. Compared with previous researches, this system comprises simpler algorithm and better amplifier system having advantages to increase a detectible distance of sound signal in spite of simple circuit. In order to verify our system's performance, we install the proposed active audition system to the home service robot, called Hombot II, which has been developed at the KIST (Korea Institute of Science and Technology), thus we confirm excellent performance by experimental results

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.2
• /
• pp.280-286
• /
• 2013

In this paper, a noise reduction system is proposed for the speech interface in intelligent TV applications. To reduce TV speaker sound which are very serious noises degrading recognition performance, a noise reduction algorithm utilizing the direct TV sound as the reference noise input is implemented. In the proposed algorithm, transfer functions are estimated to compensate for the difference between the direct TV sound and that recorded with the microphone installed on the TV frame. Then, the noise power spectrum in the received signal is calculated to perform Wiener filter-based noise cancellation. Additionally, a postprocessing step is applied to reduce remaining noises. Experimental results show that the proposed algorithm shows 88% recognition rate for isolated Korean words at 5 dB input SNR.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.12
• /
• pp.1659-1666
• /
• 2018

When the input sound is mixed voice and sound, it can be seen that the voice recognition rate is lowered due to the noise, and the speech recognition rate is improved by improving the MEMS device which is the H / W device in order to overcome the S/W processing limit. The MEMS microphone device is a device for inputting voice and is implemented in various shapes and used. Conventional MEMS microphones generally exhibit excellent performance, but in a special environment such as noise, there is a problem that the processing performance is deteriorated due to a mixture of voice and sound. To overcome these problems, we developed a newly designed MEMS device that can detect the voice characteristics of the initial input device.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2220-2223
• /
• 2003

In this paper we used Support Vector Machines(SVMs) recently proposed as the loaming method, one of Artificial Neural Network, to divide continuous speech into phonemes, an initial, medial, and final sound, and then, performed continuous speech recognition from it. Decision boundary of phoneme is determined by algorithm with maximum frequency in a short interval. Recognition process is performed by Continuous Hidden Markov Model(CHMM), and we compared it with another phoneme divided by eye-measurement. From experiment we confirmed that the method, SVMs, we proposed is more effective in an initial sound than Gaussian Mixture Models(GMMs).

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2905-2907
• /
• 1999

The meaningful speech sound block classification provides very important information in the speech recognition. The following technique of the classification is based on the DWT (discrete wavelet transform), which will provide a more fast algorithm and a useful, compact solution for the pre-processing of speech recognition. The algorithm is implemented to the unvoiced/voiced classification and the denoising.

• The Journal of the Acoustical Society of Korea
• /
• v.11 no.3
• /
• pp.14-24
• /
• 1992

This paper is a study on the consonant recognition using neural network. First, the part of consonant was separated from the sound of vowel and consonant by the use of acoustic parameter. The rate of length vs. zero crossing rate in the sound of consonant had been studied by dividing each consonant into several groups. Finally, for the purpose of consonant recognition, the composite neural network which consists of a control network and several sub-network is proposed. The control network identifies the group to which the input consonant belongs and the sub-network recognizes the consonant in each group.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.107.3-107
• /
• 2001

This paper is concerned with the development of a simple digital stethoscope system for diagnosis of cardiac disorders. This system consists of an electronic stethoscope, IC sound recorder and a notebook computer. The cardiac sound is easily acquired by the electronic stethoscope and then recorded in IC memory stick so that the digital cardiac signal can be simply transmitted to the computer for signal display, disease diagnosis, and personal history record. A software is built with functions displaying the sound graphically and replaying the sound clearly. Further, a neural network recognition system for automatic diagnosis of cardiac disorders is also added to the software.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10a
• /
• pp.4-6
• /
• 2003

A holistic representation, such as sparse ceding or independent component analysis (ICA), was successfully applied to explain early auditory processing and sound classification. In contrast, Part-based representation is an alternative way of understanding object recognition in brain. In this paper. we employ the non-negative matrix factorization (NMF)［1］which learns parts-based representation for sound classification. Feature extraction methods from spectrogram using NMF are explained. Experimental results show that NMF-based features improve the performance of sound classification over ICA-based features.

• Journal of Digital Convergence
• /
• v.13 no.10
• /
• pp.313-318
• /
• 2015

A traditional speech enhancement methods distort the sound spectrum generated according to estimation of the remaining noise, or invalid noise is a problem of lowering the speech recognition performance. In this paper, we propose a speech detection method that convergence the sound energy distribution process and sound energy parameters. The proposed method was used to receive properties reduce the influence of noise to maximize voice energy. In addition, the smaller value from the feature parameters of the speech signal The log energy features of the interval having a more of the log energy value relative to the region having a large energy similar to the log energy feature of the size of the voice signal containing the noise which reducing the mismatch of the training and the recognition environment recognition experiments Results confirmed that the improved recognition performance are checked compared to the conventional method. Car noise environment of Pause Hit Rate is in the 0dB and 5dB lower SNR region showed an accuracy of 97.1% and 97.3% in the high SNR region 10dB and 15dB 98.3%, showed an accuracy of 98.6%.