• Phonetics and Speech Sciences
• /
• v.1 no.4
• /
• pp.111-117
• /
• 2009

In this paper, a new speech endpoint detector in noisy environment is proposed. According to the previous research, the energy feature in the speech region is easily distinguished from that in the speech absent region. In conventional method, the endpoint can be found by applying the edge detection filter that finds the abrupt changing point in feature domain. However, since the frame energy feature is unstable in noisy environment, the accurate edge detection is not possible. Therefore, in this paper, the novel feature extraction method based on spectrum envelop pattern is proposed. Then, the edge detection filter is applied to the proposed feature for detection of the endpoint. The experiments are performed in the car noise environment and a substantial improvement was obtained over the conventional method.

• MALSORI
• /
• no.57
• /
• pp.113-122
• /
• 2006

Recently, many studies have been done for speech recognition in noisy environments. Particularly, the Aurora DB has been built as the common database for comparing the various feature extraction schemes. However, in general, the recognition models as well as the features have to be modified for effective noisy speech recognition. As the structure of the HTK is very complex, it is not easy to modify, the recognition engine. In this paper, we implemented a baseline recognizer based on the segmental K-means algorithm whose performance is comparable to the HTK in spite of the simplicity in its implementation.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.2E
• /
• pp.100-106
• /
• 2010

Multiple-model speech recognizer has been shown to be quite successful in noisy speech recognition. However, its performance has usually been tested using the general speech front-ends which do not incorporate any noise adaptive algorithms. For the accurate evaluation of the effectiveness of the multiple-model frame in noisy speech recognition, we used the state-of-the-art front-ends and compared its performance with the well-known multi-style training method. In addition, we improved the multiple-model speech recognizer by employing N-best reference HMMs for interpolation and using multiple SNR levels for training each of the reference HMM.

• Journal of Preventive Medicine and Public Health
• /
• v.28 no.4 s.51
• /
• pp.773-782
• /
• 1995

The purpose of this study is to reveal how the road traffic noise influences on the response of teachers and students, which composed of conversation, studying, relaxation, and physical disturbances. The research method used in this study was self-administrated questionnaire. Samples of the survey were composed of 420 persons(114 teachers and 306 students) who are exposed to traffic noise less than 65 dB(A) from two junior high schools and 410 persons(140 teachers and 270 students) from two noisy junior high schools which the road traffic noise above 65 dB(A). In the response of both of the teachers and students in noisy(above 65 dB) schools complaints of disturbances of conversation, studying, relaxation, and physical disturbances are much higher than that of less noisy schools' teachers and students(p<0.01). On the occasion of time and season, the subjects answered the traffic noise cause high troublesome and stresses in the afternoon(12:00 - 17:00) and summer respectively. It is necessary to provide governmental comprehensive and fundamental measures to improve the noisy school environments.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.2
• /
• pp.91-98
• /
• 2012

Power Quality (PQ) signal such as sag, swell, harmonics, and impulsive transients are the major issues in the operations of the power electronics based devices and microprocessor based equipments. The effectiveness of wavelet based denoising techniques and recognizing different power quality events with noise has been presented in this paper. The algorithms involved in the noisy PQ recognition system are the wavelet based denoising and the back propagation neural networks. Also, in order to verify the real-time performances of the noisy PQ recognition systems under the noisy environments, SIL(Software In the Loop) and PIL(Processor In the Loop) were carried out, resulting in the excellent recognition performances.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.9A
• /
• pp.905-915
• /
• 2007

This paper proposes a filter-based algorithm to adaptively adjust the contention window in IEEE 802.11 DCF. The proposed mechanism is focused on the general and realistic environments that have various conditions regarding to noise, media types and network load. For this flexible adaptation, Filter-based DCF(FDCF) takes a more realistic policy such as median filter concept in the image processing technologies. We can handle these various environments by adjusting the contention window size according to the result of filtering based on history-buffer. We can ignore temporarily and randomly occurred transmission failures due to noise errors and collisions in noisy environments. In addition, by changing the reference number and history-buffer size, FDCF can be extended as a general solution including previous proposed mechanism. We have confirmed that the proposed mechanism can achieve the better performance than those of previous researches in aspects of the throughput and the delay in the realistic environments.

• 한국초전도학회:학술대회논문집
• /
• v.12
• /
• pp.53-53
• /
• 2002

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.6
• /
• pp.53-61
• /
• 2000

In the speech recognition under the noisy environments, reducing the mismatch introduced between training and testing environments is an important issue. Spectral subtraction is widely used technique because of its simplicity and relatively good performance in noisy environments. In this paper, we introduce histogram method as a reliable noise estimation approach for spectral subtraction. This method has advantages over the conventional noise estimation methods in that it does not need to detect non-speech intervals and it can estimate the noise spectra even in time-varying noise environments. Even though spectral subtraction is performed using a reliable average noise spectrum by the histogram method, considerable amount of residual noise remains due to the variations of instantaneous noise spectrum about mean. To overcome this limitation, we propose a new over-estimation technique based on distribution characteristics of histogram used for noise estimation. Since the proposed technique decides the degree of over-estimation adaptively according to the measured noise distribution, it has advantages to be few the influence of the SNR variation on the noise levels. According to speaker-independent isolated word recognition experiments in car noise environment under various SNR conditions, the proposed histogram-based over-estimation technique outperforms the conventional over-estimation technique.

• Journal of the Institute of Convergence Signal Processing
• /
• v.7 no.3
• /
• pp.116-121
• /
• 2006

In this paper, we propose the dimension reduction method of multi-dimension speech feature vector for real-time adaptation procedure in various noisy environments. This method which reduces dimensions non-linearly to map the likelihood of speech feature vector and noise feature vector. The LRT(Likelihood Ratio Test) is used for classifying speech and non-speech. The results of implementation are similar to multi-dimensional speech feature vector. The results of speech recognition implementation of detected speech data are also similar to multi-dimensional(10-order dimensional MFCC(Mel-Frequency Cepstral Coefficient)) speech feature vector.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.109-112
• /
• 1999

Image segmentation is the critical first step in image information extraction for computer vision systems. Clustering methods have been used extensively in color image segmentation. Most analytic fuzzy clustering approaches are divided from the fuzzy c-means(FCM) algorithm. The FCM algorithm uses fie probabilistic constraint that the memberships of a data point across classes sum to 1. However, the memberships resulting from the FCM do not always correspond to the intuitive concept of degree of belonging or compatibility. Moreover, the FCM algorithm has considerable trouble under noisy environments in the feature space. Recently, a possibilistic approach to clustering(PCM) for solving above problems was proposed. In this paper, we used the PCM for color image segmentation. This approach differs from existing fuzzy clustering methods for color image segmentation in that the resulting partition of the data can be interpreted as a possibilistic partition. So, the problems in the FCM can be solved by the PCM. But, the clustering results by the PCM are not smoothly bounded, and they often have holes. The region growing was used as a postprocessing after smoothing the noise points in the pixel seeds. In our experiments, we illustrate that the PCM us reasonable than the FCM in noisy environments.