• 한국음향학회지
• /
• 제19권4호
• /
• pp.93-100
• /
• 2000

수중 능동소나에 의해 표적을 분류하는데 있어 표적신호의 특징파라미터는 매우 중요하다. 광대역이고 상관성이 높은 두 개의 펄스가 시간 T의 간격으로 분리되어 있을 때, 스펙트럼에서 리플간의 1/T Hz에 해당하는 TSP, 즉 피치 성분을 가진다. 음향산란 실험에 사용된 축소표적신호 또한 이러한 TSP 특징을 잘 반영하고 있다. 본 논문에서는 각 표적신호의 특징에 해당하는 TSP 정보를 FFT를 이용하여 효과적으로 추출하였다. 네 개의 표적과 각 표적의 자세각에 따라 추출된 TSP 특징파라미터를 패턴인식 기법에 적용하여 표적을 분류하고 각 표적의 특징을 분석하였다.

• 디지털융복합연구
• /
• 제11권7호
• /
• pp.209-214
• /
• 2013

음성 인식 시스템에서는 인식 성능 향상을 위한 방법으로 인간의 청취 능력을 인식 시스템에 접목하였으며 잡음 환경에서 음성 신호와 잡음을 분리하여 원하는 음성 신호만을 선택할 수 있도록 구성되었다. 하지만 실용적 측면에서 음성 인식 시스템의 성능 저하 요인으로 인식 환경 변화에 따른 잡음으로 인한 음성 검출이 정확하지 못하여 일어나는 것과 학습 모델이 일치하지 않는 것을 들 수 있다. 따라서 본 논문에서는 음성 인식 향상을 위해 감마톤을 이용하여 특징을 추출하고 음향 모델을 이용한 학습 모델을 제안하였다. 제안한 방법은 청각 장면 분석을 이용한 특징을 추출을 통해 인간의 청각 인지 능력을 반영하였으며 인식을 위한 학습 모델 과정에서 음향 모델을 이용하여 인식 성능을 향상시켰다. 성능 평가를 위해 잡음 환경의 -10dB, -5dB 신호에서 잡음 제거를 수행하여 SNR을 측정한 결과 3.12dB, 2.04dB의 성능이 향상됨을 확인하였다.

• 음성과학
• /
• 제11권4호
• /
• pp.223-232
• /
• 2004

This study investigated and compared the acoustic characteristics of the Korean stop sound [k'] in three different phonological environments: the tensified lenis stop [k'] as observed in /prek+kaci/, the fortis stop /k'/ as in /pre+k'aci/, and the fortis stop /k'/ following an obstruent as in /prek+k'aci/. The specific research question was whether or not the tensified lenis stop shares all the acoustic features with the other two kinds of fortis stops. The acoustic measures adopted in this study were H1*-H2*, VOT, length of stop closure, and $F_0$. The major findings were that the three stops showed no significant difference in all the acoustic measures except the length of stop closure. The fortis stop /k'/ following an obstruent showed significantly longer duration of stop closure than the other two stops, both of which showed no significant difference. Based on these phonetic results, this study argued that, for the proper phonological description of post-obstruent tensification, the phonological feature [slack vocal folds] of a lenis stop should be changed into [stiff vocal folds, constricted glottis] that the fortis stops should have.

• 제어로봇시스템학회논문지
• /
• 제13권8호
• /
• pp.754-759
• /
• 2007

In this paper, we proposed the Bi-Modal Sensor Fusion Algorithm which is the emotional recognition method that be able to classify 4 emotions (Happy, Sad, Angry, Surprise) by using facial image and speech signal together. We extract the feature vectors from speech signal using acoustic feature without language feature and classify emotional pattern using Neural-Network. We also make the feature selection of mouth, eyes and eyebrows from facial image. and extracted feature vectors that apply to Principal Component Analysis(PCA) remakes low dimension feature vector. So we proposed method to fused into result value of emotion recognition by using facial image and speech.

• 한국전기전자재료학회논문지
• /
• 제14권1호
• /
• pp.84-92
• /
• 2001

In this papers, we proposed the new method in order to diagnosis aging state of transformers. For wavelet transform, Daubechies filter is used, we can obtain wavelet coefficients which is used to extract feature of statistical parameters (maximum value, average value, dispersion skewness, kurtosis) about each acoustic emission signal. Also, these coefficients are used to identify normal and fault signal of internal partial discharge in transformer. As improved method for classification use neural network. Extracted statistical parameters are input into an back-propagation neural network. The number of neurons of hidden layer are obtained through Result of Cross-Validation. The network, after training, can decide whether the test signal is early aging state, alst aging state or normal state. In quantity analysis, capability of proposed method is superior to compared that of classical method.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2198-2202
• /
• 2005

In this paper we have presented a condition monitoring method of check valve using neural network. The acoustic emission sensor was used to acquire the condition signals of check valve in direct vessel injection (DVI) test loop. The acquired sensor signal pass through a signal conditioning which are consisted of steps; rejection of background noise, amplification, analogue to digital conversion, extract of feature points. The extracted feature points which represent the condition of check valve was utilized input values of fault diagnosis algorithms using pre-learned neural network. The fault diagnosis algorithm proceeds fault detection, fault isolation and fault identification within limited ranges. The developed algorithm enables timely diagnosis of failure of check valve’s degradation and service aging so that maintenance and replacement could be preformed prior to loss of the safety function. The overall process has been experimented and the results are given to show its effectiveness.

• 대한음성학회지:말소리
• /
• 제63호
• /
• pp.113-124
• /
• 2007

In this paper, we propose a use of confidence vector as an intermediate input feature for multi-stage based speech recognition architecture to improve recognition accuracy. A multi-stage speech recognition structure is introduced as a method to reduce the computational complexity of the decoding procedure and then accomplish faster speech recognition. Conventional multi-stage speech recognition is usually composed of three stages, acoustic search, lexical search, and acoustic re-scoring. In this paper, we focus on improving the accuracy of the lexical decoding by introducing a confidence vector as an input feature instead of phoneme which was used typically. We take experimental results on 220K Korean Point-of-Interest (POI) domain and the experimental results show that the proposed method contributes on improving accuracy.

• 음성과학
• /
• 제15권1호
• /
• pp.63-72
• /
• 2008

Various acoustic features were extracted and analyzed to estimate the inter- and intra-speaker variability of emotional speech. Tokens of vowel /a/ from sentences spoken with different modes of emotion (sadness, neutral, happiness, fear and anger) were analyzed. All of the acoustic features (fundamental frequency, spectral slope, HNR, H1-A1 and formant frequency) indicated greater contribution to inter- than intra-speaker variability across all emotions. Each acoustic feature of speech signal showed a different degree of contribution to speaker discrimination in different emotional modes. Sadness and neutral indicated greater speaker discrimination than other emotional modes (happiness, fear, anger in descending order of F-ratio). In other words, the speaker specificity was better represented in sadness and neutral than in happiness, fear and anger with any of the acoustic features.

• 한국음향학회지
• /
• 제18권5호
• /
• pp.58-62
• /
• 1999

본 연구에서는 한국어 연결숫자인식에 있어서 모델간의 변별력을 향상시키기 위하여 음향학적 파라메터(Acoustic Parameter)를 사용하는 것을 제안한다. 제안된 방법은 음성학적 지식에 근거하여 적절한 주파수 대역별 에너지의 비의 로그값을 추가적인 특징 파라메터로 사용한다. 실험결과, 제안된 방법을 사용함으로써 기본 인식시스템에 비해 오류율이 최고 46% 정도 감소됨을 확인할 수 있었다. 그리고 채널보상 기술을 함께 적용함으로써 69% 정도의 오류율 감소를 얻었다.

• 한국수산과학회지
• /
• 제48권2호
• /
• pp.221-232
• /
• 2015

Broadband echoes measured in live chub mackerel Scomber japonicus, goldeye rockfish Sebastes thompsoni, and fat greenling Hexagrammos otakii with different morphologies and internal characteristics were analyzed in time and frequency domains to understand the species-specific echo feature characteristics for classifying fish species. The mean echo image for each time-frequency representation dataset obtained as a function of orientation angle was extracted to mitigate the effect of fish orientation on acoustic scattering. The joint time-frequency content of the broadband echo signals was obtained using the smoothed pseudo-Wigner-Ville distribution (SPWVD). The SPWVDs were analyzed for each echo signature of the three fish species. The results show that the time-frequency analysis provided species-specific echo structure patterns and metrics of the broadband acoustic signals to facilitate fish species classification.