• The Journal of the Acoustical Society of Korea
• /
• v.34 no.3
• /
• pp.227-233
• /
• 2015

In this paper, we propose music and voice separation using kernel sptectrogram models backfitting based on log-spectral amplitude estimator. The existing method separates sources based on the estimate of a desired objects by training MSE (Mean Square Error) designed Winer filter. We introduce rather clear music and voice signals with application of log-spectral amplitude estimator, instead of adaptation of MSE which has been treated as an existing method. Experimental results reveal that the proposed method shows higher performance than the existing methods.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.4
• /
• pp.729-736
• /
• 2019

In this paper, we propose a method to improve the background sound separation performance by adding a Wiener filter to the end of the non - negative matrix factorization method. In the case of a mixed voice signal with background sound, a part that has not yet been completely separated may remain in the signal that separated first by the non-negative matrix factorization method. In this case, it can be reduced in proportion to the size of the residual signal due to the Wiener filter, so that the background sound separation or reduction effect can be expected. Experimental results show that the addition of the Wiener filter is more effective than the case of applying the non-negative matrix factorization method.

• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.1024-1034
• /
• 2019

Preference for music is determined by a variety of factors, and identifying characteristics that reflect specific factors is important for music recommendations. In this paper, we propose a method to extract the singing voice related music features reflecting various musical characteristics by using a model learned for singer identification. The model can be trained using a music source containing a background accompaniment, but it may provide degraded singer identification performance. In order to mitigate this problem, this study performs a preliminary work to separate the background accompaniment, and creates a data set composed of separated vocals by using the proven model structure that appeared in SiSEC, Signal Separation and Evaluation Campaign. Finally, we use the separated vocals to discover the singing voice related music features that reflect the singer's voice. We compare the effects of source separation against existing methods that use music source without source separation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.06a
• /
• pp.5-8
• /
• 2014

본 논문에서는 비음수 행렬 분해 (NMF) 기법을 이용하여 단일 채널에서 배경음 성분을 추출하는 알고리즘에 대해 서술한다. 이러한 배경음 성분 추출은 오디오 업믹싱 시스템을 고려하여 개발되었으며, 기존의 연구를 통하여 분리된 배경음 신호가 서라운드 채널 혹은 상방향 채널에 적용될 경우 청취자의 공간감을 향상시킬 수 있다는 사실이 이미 확인된 바 있다. 다만 기존의 기법은 음향 신호를 모두 축적하여 일괄적으로 처리해야 한다는 단점이 있어, 스트리밍 시스템이나 디지털 신호 프로세서 등을 이용한 시스템에서 사용될 수 없는 단점이 있다. 본 논문에서는 이를 해소하기 위하여 실시간 비음수 행렬 분해 기법을 이용한 배경음 추출 시스템을 고안하여 실험하였다. 실험 결과 실시간 배경음 추출 기법이 신호의 후반부에서는 원하는 대로 동작하나, 초중반에 기저가 과도하게 설정되는 문제점이 있음을 확인할 수 있었으며, 이에 대한 해결이 향후 연구 과제가 될 것이다.

• Journal of Broadcast Engineering
• /
• v.19 no.6
• /
• pp.819-825
• /
• 2014

In this paper, monaural ambient component extraction algorithm based on nonnegative matrix factorization (NMF) is described. The ambience component extraction algorithm in this paper is developed for audio upmixing system; Recent researches have shown that they can enhance listener envelopment if the extracted ambient signal is applied into the multichannel audio upmixing system. However, the conventional method stores all of the audio signal and processes all at once, so it cannot be applied to streaming system and digital signal processor (DSP) system. In this paper, the ambient component extraction algorithm based on on-line nonnegative matrix factorization is developed and evaluated to solve the problem. As a result of analysis of the processed signal with spectral flatness measures in the experiment, it was shown that the developed system can extract the ambient signal similarly with the conventional batch process system.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.07a
• /
• pp.160-163
• /
• 2012

업믹스(Upmix) 기술은 홈시어터와 같은 다채널 스피커 재생 환경에서 콘텐츠의 대부분을 차지하는 스테레오 음원을 다채널 환경에 재생하기 위한 채널 포맷 변환 기술을 말한다. 업믹스를 위한 전처리 단계로서 특정 방향으로 패닝된 주(primary)성분과 잔향 및 배경음과 같은 Ambient 성분을 분리하는 과정이 필요하다. Primary와 Ambient를 분리하기 위한 방법으로 채널 간의 상관도, 적응 필터 및 주성분 분석법(principal component analysis, PCA)이 널리 이용되고 있다. 이에 본 논문에서는 비교적 정확하게 Primary와 Ambient를 분리한다고 알려진 주성분 분석법을 이용하여 신호를 분리해 내고 이 때 주성분 분석법이 가지는 문제점을 해결한 향상된 Primary-Ambient 분리 알고리즘을 제안하였다. 제안된 알고리즘은 분리 성능이 Primary 성분이 패닝된 각도에 영향을 받지 않으며 또한 Primary 성분에 섞인 잔여 Ambient를 제거함으로써 기존의 주성분 분석법 보다 더 정확하게 Primary와 Ambient를 분리 할 수 있고 상관성이 없는 Ambient 특성을 좀 더 정확하게 반영한다.

• Journal of Broadcast Engineering
• /
• v.19 no.1
• /
• pp.64-74
• /
• 2014

The primary and ambient signal decomposition of a stereo sound is a key step to the stereo upmix. The principal component analysis (PCA) is one of the most widely used methods of primary-ambient signal decomposition. However, previous PCA-based decomposition algorithms assume that stereo sound sources are only amplitude-panned without any consideration of phase difference. So it occurs some performance degradation in case of live recorded stereo sound. In this paper, we propose a new PCA-based stereo decomposition algorithm that can consider the phase difference between the channel signals. The proposed algorithm overcomes limitation of conventional signal model using PCA with phase alignment. The phase alignment is realized by using inter-channel phase difference (IPD) which is widely used in parametric stereo coding. Moreover, Enhanced Modified PCA(EMPCA) is combined to solve the problem of conventional PCA caused by Primary to Ambient energy Ratio(PAR) and panning angle dependency. The simulation results are presented to show the improvements of the proposed algorithm.

• Journal of Advanced Navigation Technology
• /
• v.5 no.1
• /
• pp.1-10
• /
• 2001

Speech has a good characteristics of which car drivers busy to concern with miscellaneous operation can make use in convenient handling and manipulating of devices. By utilizing this, this works proposes a speaker verification method for protecting cars from being stolen and identifying a person trying to access critical on-line services. In this, continuant phonemes recognition which uses language information of speech and MLP(mult-layer perceptron) which has some advantages against previous stochastic methods are adopted. The recognition method, though, involves huge computation amount for learning, so it is somewhat difficult to adopt this in speaker verification application in which speakers should enroll themselves at real time. To relieve this problem, this works presents a solution that introduces speaker cohort models from speaker verification score normalization technique established before, dividing background speakers into small cohorts in advance. As a result, this enables computation burden to be reduced through classifying the enrolling speaker into one of those cohorts and going through enrollment for only that cohort.

• Tuberculosis and Respiratory Diseases
• /
• v.52 no.1
• /
• pp.46-53
• /
• 2002

Background: Pulmonary aspergilloma is relatively common in korea. It arises from the colonization and proliferation of Aspergillus in preexisting lung parenchymal cavities, in particular tuberculosis. The most common symptom in this disorder is hemoptysis, which mayor may not be massive and life threatening. A routine chest radiography and computed tomography (CT) are the most important diagnostic procedures. A surgical resection of the aspergilloma has recently been recommended, because of the relatively low incidence of postoperative complications than in the past. A more concentrated sample of patients with aspergilloma, who either underwent a thoracotomy or tested positive for aspergillus antibodies, were reviewed. Method : The medical records of twenty-two patients with aspergilloma, who had a proven thoracotomy (9 cases), or who tested positive for the diagnostic procedure and/or aspergillus antibodies (13 cases) from January 1995 to December 2000, were reviewed retrospectively. Results : The most common underlying lung disease was a current or old healed tuberculosis, and 3 patients had cultures of mycobacterium other than tuberculosis (MOTT). The mean time until the aspergilloma was detected 5.91 years in the healed tuberculosis cases. The others cases involved a lung abscess, bronchiectasis and without lung disease. The extrapulmonary disease was alcoholism and diabetes. Hemoptysis was most common in 72.7%. A computed tomography (CT) is useful for diagnosis. The right upper lobe, especially the posterior segment, is the most common location. Bronchial artery embolization is ineffective for a long term follow-up. A lobectomy is most common in a thoracotomy, and intra-operative and post-operative complications are rare. During follow-up, the mortality rate, not from the aspergilloma but from respiratory failure, was 13.6%. Conclusion : Aspergilloma is a common cavitary lung disease, It mainly arises from tuberculosis, either current or healed, but extra-pulmonary disease including alcoholism or diabetes are other possible risk factors. Their most common problem in aspergilloma is hemoptysis. Surgery has a low risk of post-operative complications and is recommended in relatively preserved lung function or healthy patients. Medical maneuvers including embolization, and the local insertion of certain materials needs to be studied more closely.

• Tuberculosis and Respiratory Diseases
• /
• v.49 no.3
• /
• pp.310-322
• /
• 2000

Background : Phospholipase C(PLC) plays an important role in cellular signal transduction and is thought to be critical in cellular growth, differentiation and transformation of certain malignancies. Two second messengers produced from the enzymatic action of PLC are diacylglycerol (DAG) and inositol 1, 4, 5-trisphosphate (IP3). These two second messengers are important in down stream signal activation of protein kinase C and intracellular calcium elevation. In addition, functional domains of the PLC isozymes, such as Src homology 2 (SH2) domain, Src homology 3 (SH3) domain, and pleckstrin homology (PH) domain play crucial roles in protein translocation, lipid membrane modificailon and intracellular memrane trafficking which occur during various mitogenic processes. We have previously reported the presence of PLC-${\gamma}1$, ${\gamma}2$, ${\beta}1$, ${\beta}3$, and ${\delta}1$ isozymes in normal human lung tissue and tyrosine-kinase-independent activation of phospholipase C-${\gamma}$ isozymes by tau protein and AHNAK. We had also found that the expression of AHNAK protein was markedly increased in various mstologic types of lung can∞r tissues as compared to the normallungs. However, the report concerning expression of various PLC isozymes in lung canærs and other lung diseases is lacking. Therefore, in this study we examined the expression of PLC isozymes in the paired surgical specimens taken from lung cancer patients. Methods : Surgically resected lung cancer tissue samples taken from thirty seven patients and their paired normal control lungs from the same patients, The expression of various PLC isozymes were studied. Western blot analysis of the tissue extracts for the PLC isozymes and immunohistochemistry was performed on typical samples for localization of the isozyme. Results : In 16 of 18 squamous cell carcinomas, the expression of PLC-${\gamma}1$ was increased. PLC-${\gamma}1$ was also found to be increased in all of 15 adenocarcinoma patients. In most of the non-small cell lung cancer tissues we had examined, expression of PLC-${\delta}1$ was decreased. However, the expression of PLC-${\delta}1$ was markedly increased in 3 adenocarcinomas and 3 squamous carcinomas. Although the numbers were small, in all 4 cases of small cell lung cancer tissues, the expression of PLC-${\delta}1$ was nearly absent. Conclusion : We found increased expression of PLC-${\gamma}1$ isozyme in lung cancer tissues. Results of this study, taken together with our earlier findings of AHNAK protein-a putative PLD-${\gamma}$, activator-over-expression, and the changes observed in PLC-${\delta}1$ in primary human lung cancers may provide a possible insight into the derranged calcium-inositol signaling pathways leading to the lung malignancies.