• 한국소음진동공학회논문집
• /
• 제21권10호
• /
• pp.960-966
• /
• 2011

An improved NDIF method is introduced to efficiently extract eigenvalues and eigenmodes of two-dimensional, arbitrarily shaped acoustic cavities. The NDIF method, which was developed by the authors for the eigen-mode analysis of arbitrarily shaped acoustic cavities, membranes, and plates, has the feature that it yields highly accurate eigenvalues compared with other analytical methods or numerical methods(FEM and BEM). However, the NDIF method has the weak point that the system matrix of the NDIF method depends on the frequency parameter and, as a result, a final system equation doesn's take the form of an algebra eigenvalue problem. The system matrix of the improved NDIF method developed in the paper is independent of the frequency parameter and eigenvalues and mode shapes can be efficiently obtained by solving a typical algebraic eigenvalue problem. Finally, the validity and accuracy of the proposed method is verified in two case studies, which indicate that eigenvalues and mode shapes obtained by the proposed method are very accurate compared to the exact method, the NDIF method or FEM(ANSYS).

• 말소리와 음성과학
• /
• 제3권3호
• /
• pp.57-62
• /
• 2011

Focused items in English sentences are usually accompanied by changes in acoustic manifestation. This paper investigates the acoustic characteristics of $H^*$ in English utterances produced by natives speakers of English and Korean learners of English. To obtain more reliable results, the changes of the acoustic feature values (F0, intensity, syllable duration) were normalized by a median value and a whole duration of each utterance. Acoustic values of sentences with no focused words were compared with those of sentences with focused words within each group (Americans vs. Koreans). Sentences with focused words were compared between the two groups, too. In the instances in which a significant Group x Focus Location (initial, middle and final of a sentence) interaction was obtained, further analysis testing the effect of Group on each Focus Location was conducted. The analysis revealed that Korean learners of English produced focused words with lower F0, lower intensity and shorter syllable duration than native speakers of English. However, the effect of intensity change caused by focus was not significant within each group. Further analysis examining the interaction of Group and Focus Location showed that the change in F0 produced by Korean group was significantly lower in the middle and the final positions of sentences than by American group. Implications for the intonation training were also discussed.

• 한국음향학회지
• /
• 제32권2호
• /
• pp.167-173
• /
• 2013

본 논문은 이중모음을 분류하기 위한 음향음성학적 파라메터를 연구하였다. 음향음성학적 파라메터는 성도를 통해 음성이 발성될 때 나타나는 특징을 기반으로 하여 분산분석(ANOVA) 방법을 통해 선별한 모음의 길이, 에너지 궤적, 그리고 포먼트의 차이를 이용하였다. TIMIT 데이터 베이스를 사용하였을 때, 단모음과 이중모음만을 구분하는 실험에서는 17.8% 의 밸런스 에러율(BER)을 얻을 수 있었고, /aw/, /ay/, 그리고 /oy/를 단모음과 분류하는 실험에서는 각각 32.9%, 29.9%, 그리고 20.2%의 에러율을 얻을 수 있었다. 추가적으로 진행한 실험에서, 음향음성학적 파라메터와 음성인식에 널리 쓰이고 있는 MFCC를 함께 사용하였을 경우 역시 성능향상이 나타나는 것을 확인하였다.

• 방송공학회논문지
• /
• 제17권3호
• /
• pp.519-528
• /
• 2012

음성구간을 검출하는 일반적인 방법은 음향신호로부터 특징값을 추출하여 판별식을 거치는 것이다. 그러나 잡음이 많은 환경에서 그 성능은 당연히 저하되며, 이 경우 영상신호를 이용하거나 영상과 음성을 동시에 사용함으로써 성능향상을 도모할 수 있다. 영상신호를 이용하여 음성구간을 검출하는 기존 방법들에서는 액티브 어피어런스 모델, 옵티컬 플로우, 밝기 변화 등 주로 하나의 특징값을 이용하고 있다. 그러나 음성구간의 참값은 음향신호에 의해 결정되므로 한 가지의 영상정보만으로는 음성구간을 검출하는데 한계를 보이고 있다. 본 논문에서는 입술 영역의 옵티컬 플로우와 밝기 변화 두 가지 영상정보로부터 특징값을 추출하고, 추출된 특징값들을 결합하여 음성구간을 검출하는 알고리즘을 제안하고자 한다. 또한, 음성구간 검출 알고리즘이 다른 시스템의 전처리로 활용되는 경우에 적은 계산량만으로 수행되는 것이 바람직하므로, 통계적 모델링에 의한 방법보다는 추출된 특징값으로부터 간단한 대수적 연산만으로 스코어를 산정하여 문턱값과 비교하는 방법을 제안하고자 한다. 입술 영역 검출을 위해서는 얼굴에서 가장 두드러진 특징점을 갖는 눈을 먼저 검출한 후, 얼굴의 구조와 밝기값을 이용하는 알고리즘을 제안하였다. 실험 결과 본 논문에서 제안하는 두 가지 특징값을 결합한 음성구간 검출 알고리즘이 하나의 특징값만을 이용했을 때보다 우수한 성능을 보임을 확인할 수 있다.

• 대한의용생체공학회:의공학회지
• /
• 제16권3호
• /
• pp.345-352
• /
• 1995

The LPC cepstrum coefficients, which are an acoustic features of speech signal, have been widely used as the feature parameter for various speech recognition systems and showed good performance. The vocal tract area function is a kind of articulatory feature, which is related with the physiological mechanism of speech production. This paper proposes the vocal tract area function as an alternative feature parameter for speech recognition. The linear predictive analysis using Burg algorithm and the vector quantization are performed. Then, recognition experiments for 5 Korean vowels and 10 digits are executed using the conventional LPC cepstrum coefficients and the vocal tract area function. The recognitions using the area function showed the slightly better results than those using the conventional LPC cepstrum coefficients.

• 한국안전학회지
• /
• 제27권3호
• /
• pp.20-27
• /
• 2012

Mechanical seals are one of main components of high speed centrifugal pumps. So, it is very important to detect the faults (scratch, notch, indentation, wear) of mechanical seals since the damage of seal can cause a critical failures or accidents of machinery system. In the past, many researchers mainly performed to detect the seal fault using the time signals measured from sensors. Recently, studies are focused on the development of on-line real time monitoring system. But study on the feature parameters used for fault detection of mechanical seals has a little been performed. In this paper, we showed feature parameters extracted from accelerated and acoustic signals by using the discrete wavelet transform (DWT), alpha coefficient, statistical parameters. And also verified the possibility for fault detection of mechanical seal.

• 대한음성학회지:말소리
• /
• 제55권
• /
• pp.131-142
• /
• 2005

A mismatch between the training and the test conditions often causes a drastic decrease in the performance of the speech recognition systems. In this paper, non-linear transformation techniques based on histogram equalization in the acoustic feature space are studied for reducing the mismatched condition. The purpose of histogram equalization(HEQ) is to convert the probability distribution of test speech into the probability distribution of training speech. While conventional histogram equalization methods consider only the probability distribution of a test speech, for noise-corrupted test speech, its probability distribution is also distorted. The transformation function obtained by this distorted probability distribution maybe bring about miss-transformation of feature vectors, and this causes the performance of histogram equalization to decrease. Therefore, this paper proposes a new method of calculating noise-removed probability distribution by using assumption that the CDF of noisy speech feature vectors consists of component of speech feature vectors and component of noise feature vectors, and this compensated probability distribution is used in HEQ process. In the AURORA-2 framework, the proposed method reduced the error rate by over $44\%$ in clean training condition compared to the baseline system. For multi training condition, the proposed methods are also better than the baseline system.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2007년도 추계학술대회논문집
• /
• pp.891-894
• /
• 2007

This study presents fault diagnosis of low speed bearing using support vector machine (SVM). The data used in the experiment was acquired using acoustic emission (AE) sensor and accelerometer. The aim of this study is to compare the performance of fault diagnosis based on AE signal and vibration signal with same load and speed. A low speed test rig was developed to simulate various defects with shaft speeds as low as 10 rpm under several loading conditions. In this study, component analysis was also performed to extract the feature and reduce the dimensionality of original data feature. Moreover, the classification for fault diagnosis was also conducted using original data feature without feature extraction. The result shows that extracted feature from AE sensor gave better performance in faults classification.

• Journal of Information Processing Systems
• /
• 제13권5호
• /
• pp.1135-1148
• /
• 2017

Speech recognition is one of the fascinating fields in the area of Computer science. Accuracy of speech recognition system may reduce due to the presence of noise present in speech signal. Therefore noise removal is an essential step in Automatic Speech Recognition (ASR) system and this paper proposes a new technique called combined thresholding for noise removal. Feature extraction is process of converting acoustic signal into most valuable set of parameters. This paper also concentrates on improving Mel Frequency Cepstral Coefficients (MFCC) features by introducing Discrete Wavelet Packet Transform (DWPT) in the place of Discrete Fourier Transformation (DFT) block to provide an efficient signal analysis. The feature vector is varied in size, for choosing the correct length of feature vector Self Organizing Map (SOM) is used. As a single classifier does not provide enough accuracy, so this research proposes an Ensemble Support Vector Machine (ESVM) classifier where the fixed length feature vector from SOM is given as input, termed as ESVM_SOM. The experimental results showed that the proposed methods provide better results than the existing methods.

• 전기전자학회논문지
• /
• 제13권2호
• /
• pp.132-139
• /
• 2009

본 논문에서는 핸즈프리 통신에서의 반향제거를 위한 음성 특징 기반의 동시통화 검출 기법을 제안한다. 동시통화 검출은 반향제거를 위한 적응 필터의 적응을 제어하는 역할을 하기 때문에 매우 중요한 분야이다. 이전까지의 연구에서는 동시통화 검출을 음성의 특징에 대한 고려 없이 단순히 신호처리 영역에서만 이루어졌다. 하지만 제안한 기법에서는 음성인식으로 사용되는 음성 특징을 핸즈프리 통신상에서의 근단 화자와 원단화자 사이의 차별성을 가지는 특징으로 사용하였다. 제안한 방식이 시간 축에서의 파형만을 이용하여 판단하는 동시통화검출기보다 우수한 성능을 나타내는 것을 실험을 통하여 입증하였다.