• 제목/요약/키워드: performance enhancement

검색결과 2,928건 처리시간 0.025초

잔향제거를 이용한 음성통신 시스템 성능 향상 (Performance Enhancement of Speech Communication System using Reverberation Rejection)

  • 김세영;강석엽;김기만
    • 한국정보통신학회논문지
    • /
    • 제13권10호
    • /
    • pp.2211-2217
    • /
    • 2009
  • 본 논문에서는 잔향이 존재하는 환경에서 단일 마이크로폰을 사용한 음성 개선 방법을 제시한다. 스펙트럼 차감법(Spectral Subtraction)은 스펙트럼 상에서 잔향성분 및 잡음을 제거 할 수 있는 효과적인 방법이다. 스펙트럼 차감법은 음성과 비음성 구간의 정확한 구분을 필요로 하며 성능을 향상시키기 위해 본 논문에서는 엔트로피(Entropy) 기반의 음성 구간 검출법을 적용하였다. 제시된 방법을 기존의 에너지 검출 기반의 음성 검출법을 적용한 스펙트럼 차감법과 비교하여 성능 평가를 수행하였다. SNR 및 잔향시간에 따른 잔향 제거비율을 평가지표로 사용하였으며, 시뮬레이션 결과 기존의 스펙트럼 차감법과 비교하여 제시된 방법이 우수한 성능을 보였다.

개선된 Anisotropic Gaussian 필터를 이용한 지문 영상 향상 (Fingerprint Image Enhancement using a Modified Anisotropic Gaussian Filter)

  • 조희덕;김상희;박원우
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 2003년도 신호처리소사이어티 추계학술대회 논문집
    • /
    • pp.293-296
    • /
    • 2003
  • The enhancement of fingerprint image is necessary to improve the performance of fingerprint recognition. The enhancement of fingerprint image with Gabor Filter(GF) is widely used. However GF has the weakness such as long processing time and the sensitivity to ridge frequency. To overcome these weaknesses, we propose a Modified Anisotropic Gaussian Filter(MAGF) which is modified from Anisotropic Filter proposed by S. Greenburg's(SAF). This proposed MAGF can reduce the calculation time of ridge frequency and improve the weakness of sensitivity to ridge frequency. We also explained that MAGF is better than others mathematically and experimentally.

  • PDF

음성 향상을 위한 NPHMM을 갖는 IMM 알고리즘 (IMM Algorithm with NPHMM for Speech Enhancement)

  • 이기용
    • 음성과학
    • /
    • 제11권4호
    • /
    • pp.53-66
    • /
    • 2004
  • The nonlinear speech enhancement method with interactive parallel-extended Kalman filter is applied to speech contaminated by additive white noise. To represent the nonlinear and nonstationary nature of speech. we assume that speech is the output of a nonlinear prediction HMM (NPHMM) combining both neural network and HMM. The NPHMM is a nonlinear autoregressive process whose time-varying parameters are controlled by a hidden Markov chain. The simulation results shows that the proposed method offers better performance gains relative to the previous results [6] with slightly increased complexity.

  • PDF

퍼지 멤버쉽 값을 이용한 히스토그램 명세화 (Automatic Histogram Specification Based on Fuzzy Membership Value for Image Enhancement)

  • 황태호;이정훈
    • 한국지능시스템학회:학술대회논문집
    • /
    • 한국퍼지및지능시스템학회 2002년도 추계학술대회 및 정기총회
    • /
    • pp.317-320
    • /
    • 2002
  • In this paper, an automatic histogram specification method is proposed for image enhancement, Fuzzy membership value is adopted for the representation of image histogram. The desired PDF is automatically constructed by the fuzzy membership value. Fuzzy membership value is extracted from dark membership, bright membership function and original histogram. The effectual results are demonstrated by desired PDF which meet the image enhancement requirements. The performance and effectiveness are shown by the analysis and the resultant image in comparison with histogram equalization method.

음질 개선을 통한 음성의 인식 (Speech Recognition through Speech Enhancement)

  • 조준희;이기성
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 B
    • /
    • pp.511-514
    • /
    • 2003
  • The human being uses speech signals to exchange information. When background noise is present, speech recognizers experience performance degradations. Speech recognition through speech enhancement in the noisy environment was studied. Histogram method as a reliable noise estimation approach for spectral subtraction was introduced using MFCC method. The experiment results show the effectiveness of the proposed algorithm.

  • PDF

음소기반의 순환 신경망 음성 검출기를 이용한 음성 향상 (Speech Enhancement using RNN Phoneme based VAD)

  • 이강;강상익;권장우;이상민
    • 전자공학회논문지
    • /
    • 제54권5호
    • /
    • pp.85-89
    • /
    • 2017
  • 본 논문에서는 향상된 연산 능력을 가진 하드웨어와 알고리즘의 혼합을 통하여 음성 향상을 위한 정확한 음성 검출기 구현을 목적으로 하였다. 음성은 음소의 나열로 구성되어있으며 음성 모델을 세우는데 적합한 방법은 이전의 정보를 이용하는 순환 신경망 (recurrent neural network, RNN)을 사용하는 것이다. 실제 존재하는 모든 잡음에 대하여 학습한 모델을 제시하는 것은 사실상 불가능 하므로 이를 극복하고자 음소기반 학습을 진행하였다. 학습의 결과로 세워진 모델을 기반으로 새로운 음성 신호에서 음성을 검출하고 그 결과를 이용하여 음성 향상을 진행하였다. 순환 신경망과 음소기반 학습은 프레임 별 높은 상관성을 가진 음성 신호에서 좋은 성능을 얻을 수 있었으며 음성 검출기의 성능을 검증하기 위하여 라벨 데이터와 음성 검출결과를 비교하고 다양한 잡음 환경에서 객관적 음질 평가를 진행하여 기존의 음성 향상 알고리즘과 비교하였다.

무인항공기의 내풍성 강화를 위한 제어기의 외란관측기 연구 (Disturbance Observer based PID Controller for robustness enhancement of UAVs under the presence of wind disturbance)

  • 오승조;이동진
    • 한국항공운항학회지
    • /
    • 제26권2호
    • /
    • pp.61-67
    • /
    • 2018
  • This paper presents a method to apply disturbance observer to PID controller for robustness enhancement of UAVs. The system uncertainties and disturbances bring adverse effects on performance and stability of UAVs. In this paper, we estimate the acceleration disturbances using nonlinear disturbance observer, then compensate disturbances with composite controller. By employing nonlinear disturbance observer and composite controller, we have better performance and robustness than conventional PID controller. The asymptotical stability of nonlinear disturbance observer is presented through theoretical analysis. The estimation performance of nonlinear disturbance observer is evaluated by numerical simulation. And performance of disturbance observer based PID controller is evaluated by comparing the performance with conventional PID controller.

Microwave 채널 환경에서 One-Tap 적응 등화기를 적용하는 OFDM/QPSK-DMR 시스템의 성능 분석 (Performance Analysis of OFDM/QPSK-DMR System Using One-Tap Adaptive Equalizer over the Microwave Channel)

  • 양희진;안준배;오창헌;조성준
    • 한국전자파학회:학술대회논문집
    • /
    • 한국전자파학회 2003년도 종합학술발표회 논문집 Vol.13 No.1
    • /
    • pp.398-402
    • /
    • 2003
  • In this paper, we have analyzed the performance enhancement of OFDM/QPSK-DMR(Orthogonal Frequency Division Multiplexing/Quadrature Phase Shift Keying Modulation-Digital Microwave Radio)system using BL-PSF(Band Limited-Pulse Shaping Filter) over the microwave channel. For performance enhancement, we apply the one-tap adaptive equalizer for OFDM/QPSK-DMR system and compare with the BER performance of single carrier DMR system. Computer simulations confirm that the OFDM/QPSK-DMR system using one-tap adaptive equalizer has the same BER performance for the single carrier DMR system.

  • PDF

Performance studies on concrete with recycled coarse aggregates

  • Yaragal, Subhash C.;Teja, Dumpati C.;Shaffi, Mohammed
    • Advances in concrete construction
    • /
    • 제4권4호
    • /
    • pp.263-281
    • /
    • 2016
  • Concrete continues to be the most consumed construction material in the world, only next to water. Due to rapid increase in construction activities, Construction and Demolition (C&D) waste constitutes a major portion of total solid waste production in the world. It is important to assess the amount of C&D waste being generated and analyse the practices needed to handle this waste from the point of waste utilization, management and disposal addressing the sustainability aspects. The depleting natural resources in the current scenario warrants research to examine viable alternative means, modes and methods for sustainable construction. This study reports processing Recycled Coarse Aggregates (RCA) using a rod mill, for the first time. Parameters such as amount of C&D waste for processing, nature of charge and duration of processing time have been optimized for obtaining good quality RCA. Performance of RCA based concrete and performance enhancement techniques of 50% RCA based concrete are discussed in this paper.

다결정 SnSe 열전 재료의 성능 개선 연구 동향 (Recent Studies on Performance Enhancement of Polycrystal SnSe Thermoelectric Materials)

  • 정명준;최병준
    • 한국분말재료학회지
    • /
    • 제29권2호
    • /
    • pp.152-158
    • /
    • 2022
  • Thermoelectric materials can reversely convert heat and electricity into each other; therefore, they can be very useful for energy harvesting from heat waste. Among many thermoelectrical materials, SnSe exhibits outstanding thermoelectric performance along the particular direction of a single crystal. However, single-crystal SnSe has poor mechanical properties and thus it is difficult to apply for mass production. Therefore, polycrystalline SnSe materials may be used to replace single-crystal SnSe by overcoming its inferior thermoelectric performance owing to surface oxidation. Considerable efforts are currently focused on enhancing the thermoelectric performance of polycrystalline SnSe. In this study, we briefly review various enhancement methods for SnSe thermoelectric materials, including doping, texturing, and nano-structuring. Finally, we discuss the future prospects of SnSe thermoelectric powder materials.