• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.33-36
• /
• 2007

In this paper, we investigate a fast speaker adaptation method based on eigenvoice in several noisy environments. In order to overcome its weakness against noise, we propose a noisy environment clustering method which divides the noisy adaptation utterances into utterance groups with similar environments by the vector quantization based clustering using a cepstral mean as a feature vector. Then each utterance group is used for adaptation to make an environment dependent model. According to our experiment, we obtained 19-37 % relative improvement in error rate compared with the simultaneous speaker adaptation and environmental compensation method

• 한국정보통신설비학회:학술대회논문집
• /
• 2006.08a
• /
• pp.235-240
• /
• 2006

In order to enhance receive sensitivity in noisy environment, the previous initial synchronization method of GPS receiver for reference stations adopts not only the coherent integration method but also the non-coherent integration method. However, the previous GPS initial synchronization method causes the non-coherent integration loss, which is a dominant factor among the signal acquisition losses in noisy environment. And the non-coherent integration loss increases with the strength of noise signal. In this pa-per, a GPS initial synchronization method is proposed to enhance receive sensitivity of GPS receiver for reference stations in noisy environment. This paper presents that the proposed GPS initial synchronization method suppresses the non-coherent integration loss. Furthermore, with regard to the mean acquisition time, it is shown that the number of the search cells of the proposed GPS initial synchronization method is much fewer than that of the previous GPS initial synchronization method.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.2
• /
• pp.107-112
• /
• 2006

The previous acquisition method of GPS receiver for reference station adopts not only the coherent integration method but also the non-coherent integration method in order to enhance sensitivity under noisy environment. However, under noisy environment, the previous GPS signal acquisition method causes the non-coherent integration loss which is a major factor among losses that can be caused during GPS signal acquisition. The non-coherent integration loss also increases with the strength of the received noise. This paper has intention of analyzing the performance of the GPS signal acquisition method proposed to effectively enhance sensitivity of DGPS reference receiver under noisy environment. This paper presents that the proposed GPS signal acquisition method suppresses the non-coherent integration loss through post-processing simulation. Furthermore, with regard to the mean acquisition time, it is shown that the number of search cells of the proposed GPS signal acquisition method is much fewer than that of the previous GPS signal acquisition method.

• MALSORI
• /
• no.52
• /
• pp.145-160
• /
• 2004

In this paper, a new noise compensation method based on the eigenvoice framework in feature space is proposed to reduce the mismatch between training and testing environments. The difference between clean and noisy environments is represented by the linear combination of K eigenvectors that represent the variation among environments. In the proposed method, the performance improvement of speech recognition systems is largely affected by how to construct the noisy models and the bias vector set. In this paper, two methods, the one based on MAP adaptation method and the other using stereo DB, are proposed to construct the noisy models. In experiments using Aurora 2 DB, we obtained 44.86% relative improvement with eigen-environment method in comparison with baseline system. Especially, in clean condition training mode, our proposed method yielded 66.74% relative improvement, which is better performance than several methods previously proposed in Aurora project.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.6
• /
• pp.1160-1169
• /
• 1997

This paper presents an algorithm to separate vowels from consonants in Korean characters captured in noisy environment andto recognize them. The algorithm has been originally developed for recognition of the usage code (which is represented by a single Korean character) in the license plates of Korean vehicles. It, however, could be easily adopted to other applications with minor changes, in which character recognition is needed and the environment is noisy. The key ideas of the algorithm are to localize the vowels utilizing Hough transformation and to separate the vowels from consonants utilizing mathematical morphology. We observed that the presented algorithm effectively separates vowels even if the vowels and consonants are joined together after thresholding. We also observed that our algorithm outperforms some conventional algorithms especially when the input images are noisy. The details of the comparison study are presented in the paper.

• 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.

• Nuclear Engineering and Technology
• /
• v.44 no.8
• /
• pp.977-984
• /
• 2012

The cross-correlation technique has been widely used for leakage detection of buried pipes, and this technique can be successfully applied when the leakage signal has a high signal-to-noise ratio. In the case of a power plant, the measured leakage signals obtained from the sensors may contain background noise and mechanical noise generated by adjacent machinery. In such a case, the conventional method using the cross-correlation function may fail to estimate the leakage point. In order to enhance the leakage estimation capability of a buried pipe in a noisy environment, an improved cross-correlation technique is proposed. It uses a noise rejection technique in the frequency domain to effectively eliminate the tonal noise due to rotating machinery. Experiments were carried out to verify the validity of the proposed method. The results show that even in a tonal noisy environment, the proposed method can provide more reliable means for estimating the time delay of the leakage signals.

• Speech Sciences
• /
• v.13 no.2
• /
• pp.75-84
• /
• 2006

Various methods have been proposed to overcome the problem of speech recognition in the noisy conditions. Among them, the model compensation methods like the parallel model combination (PMC) and Jacobian adaptation (JA) have been found to perform efficiently. The JA is quite effective when we have hidden Markov models (HMMs) already trained in a similar condition as the target environment. In a previous work, we have proposed an improved method for the JA to make it more robust against the changing environments in recognition. In this paper, we further improved its performance by compensating the delta-mean vectors and covariance matrices of the HMM and investigated its feasibility in the multi-model structure for the noisy speech recognition. From the experimental results, we could find that the proposed improved the robustness of the JA and the multi-model approach could be a viable solution in the noisy speech recognition.

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.149-152
• /
• 2003

This paper presents a method to find motion vectors that are closer to true motion with noisy images for simultaneous noise reduction and do-interlacing. The proposed method requires four interlaced field images: one noisy field image and three field images from which noise is already removed. The validation of motion provides accurate motion vectors and allows us to utilize them even in very noisy environment. The validated motion vectors are first used for the noise reduction, buffered and used later for the noise reduction and de -interlacing.

• Journal of Preventive Medicine and Public Health
• /
• v.22 no.3 s.27
• /
• pp.337-354
• /
• 1989

In order to evaluate the noisy environment and hearing loss of workers served in noisy working environment, the author investigated 212 manufacturing industries located in Ulsan Industrial District that could be observed for 3 successive years from 1986 to 1988. The obtained results were as follows: 1. There was increased tendency in the number of workers served in noisy working environment and that of examined of hearing loss for three years. 2. In the noise level of working environment, the number of industries less than 89dB(A) was increased every year, while more than 90dB(A) was in decreasing tendency. 3. Mean hearing loss by frequency was the most prominent in 4,000Hz, the level of hearing loss was in increasing tendency yearly, and that of left eat was higher than right ear in almost all type of industry. 4. In 1986, the level of hearing loss by type of industry was highest in manufacture of electric and electronic, and followed by paper and plywood, and metal products in right ear: that was in the order of manufacture of electric and electronic, metal products and textile products in left ear. In 1987, that was in the order of manufacture of metal products, machinery and others in right ear, and metal products, machinery and food stuff in left ear in 1988, manufacture of others, food stuff and machinery in both ear. 5. In hearing loss by service duration, right ear of 5-9 years group was higher than that of less than 5 years in 1987, whereas in 1988, the longer in service duration, the higher in the level of hearing loss in both ear. 6. In 1986, 1987 and 1988, the prevalence rate of noise-induced hearing loss were showed increasing tendency as 0.4% ,0.8% and 1.5% , respectively, and manufacture of textile products was highest(1.0%) in 1986, machinery(1.2%) in 1987 and others(2.8%) in 1988. 7. The proportion of grade E in early loss index were 76.1% (1986), 78.2% (1987) and 80.5% (1988) in left ear, 75.9% (1986), 76.4% (1987) and 75.9% (1988) in right ear.