• Title/Summary/Keyword: Pitch Smoothing

Search Result 8, Processing Time 0.031 seconds

An Improved Automatic Music Transcription Method Using TV-Filter and Optimal Note Combination (TV-필터와 최적 음표조합을 이용한 개선된 가변템포 음악채보방법)

  • Ju, Young-Ho;Lee, Joonwhoan
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.23 no.4
    • /
    • pp.371-377
    • /
    • 2013
  • This paper proposes three methods for improving the accuracy of auto-music transcription considering with time-varying tempo from monophonic sound. The first one that uses TV(Total Variation) filter for smoothing the pitch data reduces the fragmentation in the pitch segmentation result. Also, the measure finding method that combines three different ways based on pitch and energy of sound data, respectively as well as based on rules produces more stable result. In addition the temporal result of note-length encoding is corrected in optimal way that the resulted encoding minimizes the sum of quantization error in a measure while the sum of note-lengths is equal to the number of beats. In the experiment with 16 children songs, we obtained the improved result in which measure finding was complete, the accuracy of encoding for note-length and pitch was about 91.3 and 86.7, respectively.

A study on pitch detection for RUI emotion classification based on voice (RUI용 음성신호기반의 감정분류를 위한 피치검출기에 관한 연구)

  • Byun, Sung-Woo;Lee, Seok-Pil
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2015.07a
    • /
    • pp.421-424
    • /
    • 2015
  • 컴퓨터 기술이 발전하고 컴퓨터 사용이 일반화 되면서 휴먼 인터페이스에 대한 많은 연구들이 진행되어 왔다. 휴먼 인터페이스에서 감정을 인식하는 기술은 컴퓨터와 사람간의 상호작용을 위해 중요한 기술이다. 감정을 인식하는 기술에서 분류 정확도를 높이기 위해 특징벡터를 정확하게 추출하는 것이 중요하다. 본 논문에서는 정확한 피치검출을 위하여 음성신호에서 음성 구간과 비 음성구간을 추출하였으며, Speech Processing 분야에서 사용되는 전 처리 기법인 저역 필터와 유성음 추출 기법, 후처리 기법인 Smoothing 기법을 사용하여 피치 검출을 수행하고 비교하였다. 그 결과, 전 처리 기법인 유성음 추출 기법과 후처리 기법인 Smoothing 기법은 피치 검출의 정확도를 높였고, 저역 필터를 사용한 경우는 피치 검출의 정확도가 떨어트렸다.

  • PDF

Moisture Content Prediction Model Development for Major Domestic Wood Species Using Near Infrared Spectroscopy (근적외선 분광분석법을 이용한 국산 주요 수종의 섬유포화점 이하 함수율 예측 모델 개발)

  • Yang, Sang-Yun;Han, Yeonjung;Park, Jun-Ho;Chung, Hyunwoo;Eom, Chang-Deuk;Yeo, Hwanmyeong
    • Journal of the Korean Wood Science and Technology
    • /
    • v.43 no.3
    • /
    • pp.311-319
    • /
    • 2015
  • Near infrared (NIR) reflectance spectroscopy was employed to develop moisture content prediction model of pitch pine (Pinus rigida), red pine (Pinus densiflora), Korean pine (Pinus koraiensis), yellow poplar (Liriodendron tulipifera) wood below fiber saturation point. NIR reflectance spectra of specimens ranging from 1000 nm to 2400 nm were acquired after humidifying specimens to reach several equilibrium moisture contents. To determine the optimal moisture contents prediction model, 5 mathematical preprocessing methods (moving average (smoothing point: 3), baseline, standard normal variate (SNV), mean normalization, Savitzky-Golay $2^{nd}$ derivatives (polynomial order: 3, smoothing point: 11)) were applied to reflectance spectra of each specimen as 8 combinations. After finishing mathematical preprocessings, partial least squares (PLS) regression analysis was performed to each modified spectra. Consequently, the mathematical preprocessing methods deriving optimal moisture content prediction were 1) moving average/SNV for pitch pine and red pine, 2) moving average/SNV/Savitzky-golay $2^{nd}$ derivatives for Korean pine and yellow poplar. Every model contained three principal components.

A Study on the Pixel-Paralled Image Processing System for Image Smoothing (영상 평활화를 위한 화소-병렬 영상처리 시스템에 관한 연구)

  • Kim, Hyun-Gi;Yi, Cheon-Hee
    • Journal of the Institute of Electronics Engineers of Korea SD
    • /
    • v.39 no.11
    • /
    • pp.24-32
    • /
    • 2002
  • In this paper we implemented various image processing filtering using the format converter. This design method is based on realized the large processor-per-pixel array by integrated circuit technology. These two types of integrated structure are can be classify associative parallel processor and parallel process DRAM(or SRAM) cell. Layout pitch of one-bit-wide logic is identical memory cell pitch to array high density PEs in integrate structure. This format converter design has control path implementation efficiently, and can be utilize the high technology without complicated controller hardware. Sequence of array instruction are generated by host computer before process start, and instructions are saved on unit controller. Host computer is executed the pixel-parallel operation starting at saved instructions after processing start. As a result, we obtained three result that 1)simple smoothing suppresses higher spatial frequencies, reducing noise but also blurring edges, 2) a smoothing and segmentation process reduces noise while preserving sharp edges, and 3) median filtering, like smoothing and segmentation, may be applied to reduce image noise. Median filtering eliminates spikes while maintaining sharp edges and preserving monotonic variations in pixel values.

A Study on the Pixel-Parallel Usage Processing Using the Format Converter (포맷 변환기를 이용한 화소-병렬 화상처리에 관한 연구)

  • Kim, Hyeon-Gi;Lee, Cheon-Hui
    • The KIPS Transactions:PartA
    • /
    • v.9A no.2
    • /
    • pp.259-266
    • /
    • 2002
  • In this paper we implemented various image processing filtering using the format converter. This design method is based on realized the large processor-per-pixel array by integrated circuit technology. These two types of integrated structure are can be classify associative parallel processor and parallel process DRAM (or SRAM) cell. Layout pitch of one-bit-wide logic is Identical memory cell pitch to array high density PEs in integrate structure. This format converter design has control path implementation efficiently, and can be utilize the high technology without complicated controller hardware. Sequence of array instruction are generated by host computer before process start, and instructions are saved on unit controller. Host computer is executed the pixel-parallel operation starting at saved instructions after processing start. As a result, we obtained three result that 1) simple smoothing suppresses higher spatial frequencies, reducing noise but also blurring edges, 2) a smoothing and segmentation process reduces noise while preserving sharp edges, and 3) median filtering may be applied to reduce image noise. Median filtering eliminates spikes while maintaining sharp edges and preserving monotonic variations in pixel values.

Power Fluctuation Reduction of Pitch-Regulated MW-Class PMSG based WTG System by Controlling Kinetic Energy

  • Howlader, Abdul Motin;Urasaki, Naomitsu;Yona, Atsushi;Senjyu, Tomonobu;Saber, Ahmed Yousuf
    • Journal of international Conference on Electrical Machines and Systems
    • /
    • v.1 no.2
    • /
    • pp.116-124
    • /
    • 2012
  • Wind is an abundant source of natural energy which can be utilized to generate power. Wind velocity does not remain constant, and as a result the output power of wind turbine generators (WTGs) fluctuates. To reduce the fluctuation, different approaches are already being proposed, such as energy storage devices, electric double layer capacitors, flywheels, and so on. These methods are effective but require a significant extra cost to installation and maintenance. This paper proposes to reduce output power fluctuation by controlling kinetic energy of a WTG system. A MW-class pitch-regulated permanent magnet synchronous generator (PMSG) is introduced to apply a power fluctuation reducing method. The major advantage of this proposed method is that, an additional energy storage system is not required to control the power fluctuation. Additionally, the proposed method can mitigate shaft stress of a WTG system. Which is reflected in an enhanced reliability of the wind turbine. Moreover, the proposed method can be changed to the maximum power point tracking (MPPT) control method by adjusting an averaging time. The proposed power smoothing control is compared with the MPPT control method and verified by using the MATLAB SIMULINK environment.

Numerical Analysis of 2D, Steady, Inviscid Transonic Flow Through Stationary Compressor Cascade (2차원 직선 정지 익렬에서의 비점성 천이음속유동에 관한 수치적 해석)

  • 최인환;이진호;조강래
    • Transactions of the Korean Society of Mechanical Engineers
    • /
    • v.14 no.5
    • /
    • pp.1244-1253
    • /
    • 1990
  • Time-Marching methods solving Euler equations are used for calculation of two-dimensional, steady, inviscid flow through a stationary compressor cascade. Calculation method is based on the Denton`s opposed difference scheme. A smoothing in the axial direction is used to increase the stability of solution. The computational grid consists of quadrilateral elements, one of which has four nodes at each corner and the grid points on the upper periodic boundaries are located one pitch away from those on the lower boundaries to satisfy the periodicity condition. Results of calculation show good agreement with other computational and experimental results, proving that the present method of calculation should be applied with confidence for the cascade flow with shock wave.

The signal processing of moire fringes obtained by the superposition of a fixed self-imaging elongated circular(EC) grating and a moved EC grating for the precise measurement of linear transverse displacements (정밀한 선형 횡변위 측정용 elongated circular 격자의 자체결상을 이용한 무아레 무늬의 신호처리법)

  • Lee Sang Il;Baek Seung Sun;Jo Jae Heung
    • Korean Journal of Optics and Photonics
    • /
    • v.15 no.5
    • /
    • pp.435-442
    • /
    • 2004
  • We obtained precise linear transverse displacements from the results of signal processing on moire fringes measured by the superposition of a fixed self-imaging elongated circular(EC) grating and a moved EC grating. The linear displacement less than one pitch of the moving EC grating was calculated from the position of a bright moire fringe generated on the linear grating part of the EC gratings. The moire signals were high-frequency-filtered, smoothed, curve-fitted, and first-differentiated moire signals in sequence. Also the linear displacement created by movement by the unit of integer times of a pitch was readily measured by the count of the even number of zero-crossing points corresponding to bright moire fringes obtained by the above same processing without curve fitting. Then we can measure linear transverse displacements with the accuracy of better than 3 %, which are more accurate values than those by the traditional visual method within the displacement of 80 ${\mu}{\textrm}{m}$.