• Title/Summary/Keyword: Speech presence probability

Search Result 10, Processing Time 0.099 seconds

Improved speech enhancement of multi-channel Wiener filter using adjustment of principal subspace vector (다채널 위너 필터의 주성분 부공간 벡터 보정을 통한 잡음 제거 성능 개선)

  • Kim, Gibak
    • The Journal of the Acoustical Society of Korea
    • /
    • v.39 no.5
    • /
    • pp.490-496
    • /
    • 2020
  • We present a method to improve the performance of the multi-channel Wiener filter in noisy environment. To build subspace-based multi-channel Wiener filter, in the case of single target source, the target speech component can be effectively estimated in the principal subspace of speech correlation matrix. The speech correlation matrix can be estimated by subtracting noise correlation matrix from signal correlation matrix based on the assumption that the cross-correlation between speech and interfering noise is negligible compared with speech correlation. However, this assumption is not valid in the presence of strong interfering noise and significant error can be induced in the principal subspace accordingly. In this paper, we propose to adjust the principal subspace vector using speech presence probability and the steering vector for the desired speech source. The multi-channel speech presence probability is derived in the principal subspace and applied to adjust the principal subspace vector. Simulation results show that the proposed method improves the performance of multi-channel Wiener filter in noisy environment.

Double-Talk Detection Based on Soft Decision for Acoustic Echo Suppression (음향학적 반향 제거를 위한 Soft Decision 기반의 동시통화 검출)

  • Park, Yun-Sik;Chang, Joon-Hyuk
    • The Journal of the Acoustical Society of Korea
    • /
    • v.28 no.3
    • /
    • pp.285-289
    • /
    • 2009
  • In this paper, we propose a novel double-talk detection (DTD) technique based on soft decision in the frequency domain. In the proposed method, global near-end speech presence probability (GNSPP) considering the statistical model assumption and voice activity detection (VAD) decision of the near-end and far-end signal are applied to the DTD algorithm in the frequency domain instead of the traditional hard decision scheme using cross-correlation coefficients. The performance of the proposed algorithm is evaluated by the objective test under various environments, and yields better results compared with the conventional scheme.

An Optimally-Modified Multichannel Wiener Filter Using Speech Presence Probability (음성존재확률을 이용한 최적 변형 다채널 위너 필터)

  • Jeong, Sangbae;Kim, Youngil
    • Smart Media Journal
    • /
    • v.7 no.3
    • /
    • pp.9-15
    • /
    • 2018
  • This paper proposes an optimal gain modification method of the Multichannel Wiener filter (MWF) using speech presence probabilities. Conventional gain modification methods of MWFs have the problem of the increase of speech distortions while reducing residual noises with its relative heuristic approach. However, the proposed optimal gain modification method, derived by solving the unconstrained minimization problem of the probability-involved cost function, reduces amounts of residual noises and signal distortions simultaneously. Through an evaluation of the filtered waveforms and spectrograms, it is verified that the proposed method results in an improved SNR with less signal distortions compared to the conventional MWF.

Intelligibility Enhancement of Multimedia Contents Using Spectral Shaping (스펙트럼 성형기법을 이용한 멀티미디어 콘텐츠의 명료도 향상)

  • Ji, Youna;Park, Young-cheol;Hwang, Young-su
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.53 no.11
    • /
    • pp.82-88
    • /
    • 2016
  • In this paper, we propose an intelligibility enhancement algorithm for multimedia contents using spectral shaping. The dialogue signals is essential to understand the plot of audio-visual media contents such as movie and TV. However, the non-dialogue components as like sound effects and background music often degrade the dialogue clarity. To overcome this problem, this paper tries to improves the dialogue clarity of audio soundtracks which contain important cues for the visual scenes. In the proposed method, the dialogue components are first detected by soft masker based on speech presence probability (SPP) which is widely used in speech enhancement field. Then, extracted dialogue signals are applied to the spectral shaping method. It reallocate the spectral-temporal energy of speech to enhanced the intelligibility. The total energy is maintained as unchanged via a loudness normalization process to prevent saturation. The algorithm was evaluated using the modeled and real movie soundtracks and it was shown that the proposed algorithm enhances the dialogue clarity while preserving the total audio power.

Speech Enhancement based on Minima Controlled Recursive Averaging Technique Incorporating Second-order Conditional Maximum a posteriori Criterion (2차 조건 사후 최대 확률 기반 최소값 제어 재귀평균기법을 이용한 음성향상)

  • Kum, Jong-Mo;Chang, Joon-Hyuk
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.46 no.4
    • /
    • pp.132-138
    • /
    • 2009
  • In this paper, we propose a novel approach to improve the performance of minima controlled recursive averaging (MCRA) which is based on the second-order conditional maximum a posteriori (CMAP). From an investigation of the MCRA scheme, it is discovered that the MCRA method cannot take full consideration of the inter-frame correlation of voice activity since the noise power estimate is adjusted by the speech presence probability depending on an observation of the current frame. To avoid this phenomenon, the proposed MCRA approach incorporates the second-order CMAP criterion in which the noise power estimate is obtained using the speech presence probability conditioned on both the current observation and the speech activity decisions in the previous two frames. Experimental results show that the proposed MCRA technique based on second-order conditional MAP yields better results compared to the conventional MCRA method.

Feature Vector Processing for Speech Emotion Recognition in Noisy Environments (잡음 환경에서의 음성 감정 인식을 위한 특징 벡터 처리)

  • Park, Jeong-Sik;Oh, Yung-Hwan
    • Phonetics and Speech Sciences
    • /
    • v.2 no.1
    • /
    • pp.77-85
    • /
    • 2010
  • This paper proposes an efficient feature vector processing technique to guard the Speech Emotion Recognition (SER) system against a variety of noises. In the proposed approach, emotional feature vectors are extracted from speech processed by comb filtering. Then, these extracts are used in a robust model construction based on feature vector classification. We modify conventional comb filtering by using speech presence probability to minimize drawbacks due to incorrect pitch estimation under background noise conditions. The modified comb filtering can correctly enhance the harmonics, which is an important factor used in SER. Feature vector classification technique categorizes feature vectors into either discriminative vectors or non-discriminative vectors based on a log-likelihood criterion. This method can successfully select the discriminative vectors while preserving correct emotional characteristics. Thus, robust emotion models can be constructed by only using such discriminative vectors. On SER experiment using an emotional speech corpus contaminated by various noises, our approach exhibited superior performance to the baseline system.

  • PDF

Statistical Model-Based Voice Activity Detection Using the Second-Order Conditional Maximum a Posteriori Criterion with Adapted Threshold (적응형 문턱값을 가지는 2차 조건 사후 최대 확률을 이용한 통계적 모델 기반의 음성 검출기)

  • Kim, Sang-Kyun;Chang, Joon-Hyuk
    • The Journal of the Acoustical Society of Korea
    • /
    • v.29 no.1
    • /
    • pp.76-81
    • /
    • 2010
  • In this paper, we propose a novel approach to improve the performance of a statistical model-based voice activity detection (VAD) which is based on the second-order conditional maximum a posteriori (CMAP). In our approach, the VAD decision rule is expressed as the geometric mean of likelihood ratios (LRs) based on adapted threshold according to the speech presence probability conditioned on both the current observation and the speech activity decisions in the pervious two frames. Experimental results show that the proposed approach yields better results compared to the statistical model-based and the CMAP-based VAD using the LR test.

A Statistical Model-Based Voice Activity Detection Employing the Conditional MAP Criterion with Spectral Deviation (조건 사후 최대 확률과 음성 스펙트럼 변이 조건을 이용한 통계적 모델 기반의 음성 검출기)

  • Kim, Sang-Kyun;Chang, Joon-Hyuk
    • The Journal of the Acoustical Society of Korea
    • /
    • v.30 no.6
    • /
    • pp.324-329
    • /
    • 2011
  • In this paper, we propose a novel approach to improve the performance of a statistical model-based voice activity detection (VAD) which is based on the conditional maximum a posteriori (CMAP) with deviation. In our approach, the VAD decision rule is expressed as the geometric mean of likelihood ratios (LRs) based on adapted threshold according to the speech presence probability conditioned on both the speech activity decisions and spectral deviation in the pervious frame. Experimental results show that the proposed approach yields better results compared to the CMAP-based VAD using the LR test.

Speech Enhancement Based on Minima Controlled Recursive Averaging Technique Incorporating Conditional MAP (조건 사후 최대 확률 기반 최소값 제어 재귀평균기법을 이용한 음성향상)

  • Kum, Jong-Mo;Park, Yun-Sik;Chang, Joon-Hyuk
    • The Journal of the Acoustical Society of Korea
    • /
    • v.27 no.5
    • /
    • pp.256-261
    • /
    • 2008
  • In this paper, we propose a novel approach to improve the performance of minima controlled recursive averaging (MCRA) which is based on the conditional maximum a posteriori criterion. A crucial component of a practical speech enhancement system is the estimation of the noise power spectrum. One state-of-the-art approach is the minima controlled recursive averaging (MCRA) technique. The noise estimate in the MCRA technique is obtained by averaging past spectral power values based on a smoothing parameter that is adjusted by the signal presence probability in frequency subbands. We improve the MCRA using the speech presence probability which is the a posteriori probability conditioned on both the current observation the speech presence or absence of the previous frame. With the performance criteria of the ITU-T P.862 perceptual evaluation of speech quality (PESQ) and subjective evaluation of speech quality, we show that the proposed algorithm yields better results compared to the conventional MCRA-based scheme.

Low-Complexity Speech Enhancement Algorithm Based on IMCRA Algorithm for Hearing Aids (보청기를 위한 IMCRA 기반 저연산 음성 향상 알고리즘)

  • Jeon, Yuyong;Lee, Sangmin
    • Journal of rehabilitation welfare engineering & assistive technology
    • /
    • v.11 no.4
    • /
    • pp.363-370
    • /
    • 2017
  • In this paper, we proposed a low-complexity speech enhancement algorithm based on a improved minima controlled recursive averaging (IMCRA) and log minimum mean square error (logMMSE). The IMCRA algorithm track the minima value of input power within buffers in local window and identify the speech presence using ratio between input power and its minima value. In this process, many number of operations are required. To reduce the number of operations of IMCRA algorithm, minima value is tracked using time-varying frequency-dependent smoothing based on speech presence probability. The proposed algorithm enhanced speech quality by 2.778%, 3.481%, 2.980% and 2.162% in 0, 5, 10 and 15dB SNR respectively and reduced computational complexity by average 9.570%.