• 한국통신학회:학술대회논문집
• /
• 한국통신학회 1984년도 춘계학술발표회논문집
• /
• pp.60-62
• /
• 1984

Several pitch detection algorithms are studied and compared with the standard pitch detector in a terms of some kinds of errors and each of speaders. Various types of errors are defined, and rank the performance of pitch detectors.

• International Journal of Precision Engineering and Manufacturing
• /
• 제8권1호
• /
• pp.52-58
• /
• 2007

We propose a new contact detection algorithm for fine pitch wire bonding. Fast and stable contact detection of the z-axis in wire bonding is extremely important to maintain the quality of fine pitch gold wire bonding processes, which use a small pad less than $70{\mu}m$ in diameter. A small perturbation in the contact detection time causes a large difference in the size of the formed squashed ball. The new detection method is based on a statistical approach and designed for a discrete Kalman filter. It is faster and has smaller detection time variations than conventional detection methods. Experimental results are presented to demonstrate the advantages of the proposed algorithm.

• 말소리와 음성과학
• /
• 제4권2호
• /
• pp.51-59
• /
• 2012

The purpose of this study is to examine the pitch pattern of Korean accentual phrases produced by Chinese Korean-learners in the reading of a Korean text. Korean accentual phrase is determined by a specific F0 contour. And the pitch contour of APs differ depending on their length and the nature of initial segment. In order to examine if Chinese speakers are also aware such a phonetic properties, we have examined the AP pitch contours produced by 15 Chinese speakers differing in proficiency, and compared them to pitch contours produced by six Korean native speakers. The results show that Chinese speakers' pitch errors were observed in initial segment-tone interaction and in type of pitch patterns. However, even though Chines speakers produced the same type of pitch patterns, internal tonal modulation differs from native speakers. Finally, on the basis of theses results, we proposed a teaching method that visualizes the F0 contour.

• 한국음향학회지
• /
• 제13권5호
• /
• pp.77-82
• /
• 1994

음성신호 처리에서, 피치를 정확하게 찾아내는 것이 매우 중요하다. 현재까지 많은 피치 검출 방법들이 제안되어 왔지만, 광범위한 화자와 다양한 음성 데이터로부터 정확한 피치를 찾는 것은 어렵다. 따라서 본 논문에서는 G-peak 검출을 이용한 새로운 피치 검출 알고리즘을 제안한다. 이 방법은 G-peak 의 MZCI (최대 영교차 간격) 을 LPF (low-pass filter)의 차단대역폭으로 결정하여 음성신호의 피치를 검출하는 방법이다. 본 알고리즘은 0dB SNR 환경 하에서 3.36%의 그로스 에러를 나타내는 잡음에 강인한 방법이다. 또한 잡음이 없는 음성의 그로스 에러는 0.18%였고, 모든 과정은 고속 처리가 가능하다.

• 한국음향학회지
• /
• 제16권2호
• /
• pp.36-40
• /
• 1997

음성신호처리 분야에서 정확한 피치검출은 중요하고 필요하다. 지금까지 제안된 피치검출 알고리즘들은 음성신호의 다양성으로 인해 피치를 정확히 검출하기가 어렵다. 본 논문에서는 PCM과 같은 균일 양자화기의 잔여신호에 대해 음성신호의 기본주기를 검출하는 새로운 피치검출법을 제안하였다. 제안한 방법은 무잡음 음성에 대해 평균 0.25%의 조오율이 그리고 0dB의 SNR에 대해서는 평균 3.39%의 조오율이 나타나는 정확성을 보였다. 또한 음소의 천이영역이나 배경잡음 하에서도 피치검출의 정확도가 개선된 피치검출의 결과를 얻었다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 추계학술대회 논문집 학회본부
• /
• pp.149-153
• /
• 1995

In this paper, wavelet transform with multi-resolution property is used to improve the accuracy of pitch estimation of speech signal. Pitch detection of speech signal is based on the local maxima by using wavelet transform. The wavelet transform of a signal is a multiscale decomposition that is well localized in space and frequency. The proposed pitch defection algorithm is suitable for both low-pitched and high-pitched speakers.

• 음성과학
• /
• 제5권1호
• /
• pp.23-33
• /
• 1999

Mallat has shown that, with a proper choice of wavelet function, the local maxima of wavelet transformed signal indicate a sharp variation in the signal. Since the glottal closure causes sharp discontinuities in the speech signal, dyadic wavelet transform can be useful for detecting abrupt change in the voiced sounds, i.e., epochs. In this paper, we investigate the glottal closure instants obtained from the wavelet analysis of speech signal and compare them with those obtained from the EGG signal. Then, we detect pitch period of speech signal on the basis of these results. Experimental results demonstrated that local maxima of wavelet transformed signal give accurate estimation of epoch and pitch periods of voiced sound obtained by the proposed algorithm also correspond to those from EGG well.

• 음성과학
• /
• 제11권3호
• /
• pp.157-164
• /
• 2004

Human has average pitch-level when speak naturally. That is 'Habitual pitch level'. However, if noise added at speech, the pitch-wave is changed irregularly. We can estimate noise level of speech by using this point. This paper calculates energy level of the input speech, pitch period from of above limited energy level by NAMDF (Normalized Average Magnitude Difference Function) method, after cut each frame by pitch period unit, and propose a method that estimate noise level through closed pitch of input speech.

• 방송공학회논문지
• /
• 제25권4호
• /
• pp.576-586
• /
• 2020

레이더나 라이더 센서를 활용한 야구 경기 분석은 많은 비용이 요구된다. 본 논문에서는 중계 비디오에서 피치 샷과 타구 샷을 검출하고, 카메라의 움직임 기반 타구 궤적 생성 알고리즘을 제안한다. 제안하는 알고리즘은 객체 검출과 옵티컬 플로우 기반 피치 샷과 타구 샷 검출 이후, 프레임 간 변환 관계를 통해 프레임 내 타구 위치와 타구 궤적을 계산한다. 제안 방법은 KBO 중계 영상 시퀀스 3개에 대해 성능을 평가하였고 피치 샷과 타구 샷 검출 정확도와 검출률은 89-95[%] 이내의 성능을 보였으며, 평균 타구 위치 거리차이는 13.6[m], 방향 차이 7.5°, 파울 분류 정확도 98.6%의 성능을 보였다.

• Structural Monitoring and Maintenance
• /
• 제4권4호
• /
• pp.381-396
• /
• 2017

Structural health monitoring (SHM) is a necessity for reliable and efficient functioning of engineering systems. Damage detection (DD) is a crucial component of any SHM system. Lamb waves are a popular means to DD owing to their sensitivity to small damages over a substantial length. This typically involves an active sensing paradigm in a pitch-catch setting, that involves two piezo-sensors, a transmitter and a receiver. In this paper, we propose a data-intensive DD approach for beam structures using high frequency signals acquired from beams in a pitch-catch setting. The key idea is to develop a statistical learning-based approach, that harnesses the inherent sparsity in the problem. The proposed approach performs damage detection, localization in beams. In addition, quantification is possible too with prior calibration. We demonstrate numerically that the proposed approach achieves 100% accuracy in detection and localization even with a signal to noise ratio of 25 dB.