• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.4
• /
• pp.649-655
• /
• 2006

This paper proposes a HMM-based recognition method using DMSVQ(Dynamic Multi-Section Vector Quantization) codebook by DMS model and double spectral feature, as a method on the speech recognition of speaker-independent. LPC cepstrum parameter is used as a instantaneous spectral feature and LPC cepstrum's regression coefficient is used as a dynamic spectral feature These two spectral features are quantized as each VQ codebook. HMM using DMS model is modeled by receiving instantaneous spectral feature and dynamic spectral feature by input. Other experiments to compare with the results of recognition experiments using proposed method are implemented by the various conventional recognition methods under the equivalent environment of data and conditions. Through the experiment results, it is proved that the proposed method in this paper is superior to the conventional recognition methods.

• Annual Conference on Human and Language Technology
• /
• 1989.10a
• /
• pp.120-125
• /
• 1989

음성 신호에는 언어정보이외에 여러 요인에 의한 정보가 포함되어 있어서, 문자와 일대일로 대응되는 분절을 정확하게 검출하기가 어렵다. 본 연구에서는 선형 예측계수 (LPC) 스펙트럼의 첨두 부분을 강조한 이진 (binary) 스펙트럼을 제안하고, 이를 바탕으로 음의 안정영역과 천이영역을 통합하여 음향특징을 추출하고자 한다. 각 영역의 특징은 이진 스펙트럼을 누적하여 구하며, 통합적인 특징은 각 영역의 특징을 결합한 관계적 특징으로 나타낸다. 제 2 차 포르만트 주파수의 궤적을 관계적 특징으로 하여, 양순 비음과 치조 비음을 구별한 결과, 모음의 문맥과 화자에 비교적 독립적인 인식결과를 얻을 수 있었다. 또한 이진 스펙트럼이 원래의 스펙트럼에 포함된 정보를 유지하는지 검토하기 위해, 같은 거리척도 (distance measure) 에 의해 인식 실험한 결과 이진 스펙트럼의 성능이 오히려 우수하게 나타났으며, 관계적 이진 스펙트럼의 경우 화자에 따른 변화가 더욱 적었다. 음성에 백색 잡음 (Gaussian white noise)을 더하여 잡음음성 (noisy speech) 을 만든 뒤, 같은 방법으로 실험한 결과도 유사한 인식결과를 얻을 수 있어 제안된 이진 스펙트럼의 유효성을 확인하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.4
• /
• pp.265-269
• /
• 2010

This paper proposes a novel spectral audio feature, spectral contrast MFCC (SCMFCC), and studies its performance on the musical genre classification. For a successful musical genre classifier, extracting features that allow direct access to the relevant genre-specific information is crucial. In this regard, the features based on the spectral contrast, which represents the relative distribution of the harmonic and non-harmonic components, have received increased attention. The proposed SCMFCC feature utilizes the spectral contrst on the mel-frequency cepstrum and thus conforms the conventional MFCC in a way more relevant for musical genre classification. By performing classification test on the widely used music DB, we compare the performance of the proposed feature with that of the previous ones.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.5
• /
• pp.239-243
• /
• 2008

This paper proposes a new audio identification method based on a combination of the instantaneous and dynamic spectral features of the audio spectrum. Especially we propose the spectro-temporal subband centroids that are easy to compute and effective to summarize the instantaneous and dynamic spectral variations. Experimental results demonstrate that the identification performance can be greatly improved by combining both the spectral and the temporal subband centroids.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.63-65
• /
• 2012

본 논문에서는 입력된 음성이 남성화자인지 여성화자인지를 구분하는 FFT 스펙트럼 및 LPC 켑스트럼 입력에 의한 성별인식 알고리즘을 제안한다. 본 논문에서는 특히 남성화자와 여성화자의 특징벡터를 비교 분석하여, 이러한 남녀의 음향학적인 특징벡터의 차이점을 이용하여 신경회로망에 의한 성별 인식에 대한 실험을 수행한다. 특히 12차의 LPC 켑스트럼 및 8차의 저역 FFT 스펙트럼의 특징벡터를 사용한 경우에, 남성화자 및 여성화자에 대해서 양호한 남녀 성별인식률이 구해졌다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.770-772
• /
• 2016

본 논문에서는 음성신호처리 시스템에 유용하게 사용되는 음성신호의 특징 파라미터를 출력하는 스펙트럼 필터모델을 사용하여, 배경잡음 환경 하에서 음성신호 중의 잡음을 제거하는 알고리즘을 제안한다. 따라서 본 논문에서는 배경잡음을 제거할 때 고려해야 할 인간의 청각특성이 포함된 음성의 진폭 스펙트럼에 의한 청각필터의 특성을 도입한다. 본 논문의 실험에서 사용한 성능평가의 방법으로는 음절 명료도의 테스트에 적합한 주관적인 평가인 주파수 영역에서의 스펙트럼 왜곡률(Spectral Distortion, SD)을 사용하여 실험결과를 비교하고 고찰한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.9C
• /
• pp.876-883
• /
• 2003

In this paper, we propose an algorithm for organ recognition in ultrasound images using log power spectrum. The main procedure of the algorithm consists of feature extraction and feature classification. In the feature extraction, as a translation invariant feature, log power spectrum is used for extracting the information on echo of the organs tissue from a preprocessed input image. In the feature classification, Mahalanobis distance is used as a measure of the similarity between the feature of an input image and the representative feature of each class. Experimental results for real ultrasound images show that the proposed algorithm yields the improvement of maximum 30% recognition rate than the recognition algorithm using power spectrum and Euclidean distance, and results in better recognition rate of 10-40% than the recognition algorithm using weighted quefrency complex cepstrum.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.2
• /
• pp.80-85
• /
• 2011

Alzheimer's disease and Parkinson's disease are the most common neurodegenerative disorders. In this paper, we proposed a feature extraction method for classification of AD and PD based on micro-Raman spectra from platelet. The first step of the preprocessing is a simple smoothing followed by background elimination to the original spectra to make it easy to measure the intensity of the peaks. The last step of the preprocessing was peak alignment with the reference peak. After the inspection of the preprocessed spectra, we found that proportion of two peak intensity at 743 and $757cm^{-1}$ and peak intensity at 1248 and $1448cm^{-1}$ are the most discriminative features. Then we apply mapstd method for normalization. The method returned data with means to 0 and deviation to 1. With these three features, the classification result involving 263 spectra showed about 95.8% true classification in case of MAP(maximum a posteriori probability).

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.5
• /
• pp.2298-2304
• /
• 2012

X-ray fluorescence spectrum analysis method can be applied in many areas, including concentration analysis of RoHS elements and heavy metals etc. and we can get analysis results in a relatively short time. Because X-ray fluorescence spectrum has noises and several artifacts that lowers the accuracy of the analysis. This paper analyzes the characteristics of the noise of the X-ray fluorescence spectrum to increase the accuracy of analysis. X-ray fluorescence spectrum have the characteristics of shot noise (Poisson noise), so the noise size is relatively large in the small signal portion and the noise the size is relatively small in the large part of the signal. Existing methods of analysis and to remove noises is a method for general purposes algorithm. Since these algorithm does not reflect these noise characteristics, we get distorted analysis result. We can design efficient noise remove algorithm based on the accurate noise analysis method, and we expect high accuracy results of the elemental concentration analysis result.

• The Journal of the Acoustical Society of Korea
• /
• v.10 no.1
• /
• pp.52-60
• /
• 1991

This paper describes the study on isolated word recognition by using DHMM(Dynamic Hidden Markov Model) which has dynamic feature of spectrum as a parameter. This paper discusses speech recognition experiment basedon HMM which can evaluate not only instantaneous spectral features but also dynamic spectral features. LPC cepstrum parameters is used as a static feature and LPC cepstrum's regression coefficient is used as a dynamic feature. These two features are quantized by each VQ codebook. DHMM is modeled by receiving static vector and dynamic vector by input. In the whole experiment, as recognition experiment using DHMM shows 92.7% of recognition rate while the experiment using conventional HMM shows 88.8% of recognition rate, DHMM proved to be a useful model.