Full-reference Objective Quality Evaluation for Noise-reduced Speech Considering Effect of Musical Noise
نویسندگان
چکیده
In this paper, we propose a full-reference objective quality evaluation method for noise-reduced speech. In the proposed method, acoustical features are extracted from input noisereduced speech and its original clean version, and then the speech quality and the noise quality are estimated separately from these features. Finally, the overall quality is determined from the estimates of the speech quality and the noise quality. The basic idea of the proposed method is similar to that of the non-reference method that we previously proposed but has two attractive features. The first is to use an improved overall quality estimation model. The other is to consider the effect of musical noise, which is known as annoying residual noise with tonal components. Experimental results confirmed that the proposed method gives accurate estimates of the overall quality.
منابع مشابه
A Novel Frequency Domain Linearly Constrained Minimum Variance Filter for Speech Enhancement
A reliable speech enhancement method is important for speech applications as a pre-processing step to improve their overall performance. In this paper, we propose a novel frequency domain method for single channel speech enhancement. Conventional frequency domain methods usually neglect the correlation between neighboring time-frequency components of the signals. In the proposed method, we take...
متن کاملA Perceptual Approach to Reduce Musical Noise Using Critical Bands Tonality Coefficients and Masking Thresholds
Traditional noise reduction techniques have the drawback of generating an annoying musical noise. A new scheme for speech enhancement in high noise environment is developed by considering human auditory system masking characteristics. The new scheme considers the masking threshold of both noisy speech and the denoised one, to detect musical noise components. To make them inaudible, they are set...
متن کاملAn Improved Multi-Band Spectral Subtraction for Enhancing Speech Degraded by Non-Stationary Noises
This paper proposes an improved multi-band spectral subtraction algorithm with the goal of improving the quality of speech signal in various noise environments. In the proposed enhancement algorithm, the whole speech spectrum is divided into different uniformly spaced continuous frequency bands and spectral over-subtraction is performed independently, in each band. The proposed algorithm uses a...
متن کاملSingle-channel speech enhancement using spectral subtraction in the short-time modulation domain
In this paper we investigate the modulation domain as an alternative to the acoustic domain for speech enhancement. More specifically, we wish to determine how competitive the modulation domain is for spectral subtraction as compared to the acoustic domain. For this purpose, we extend the traditional analysis-modification-synthesis framework to include modulation domain processing. We then comp...
متن کاملAdaptive filtering for attenuating musical noise caused by spectral subtraction
A method of alleviating processing distortion caused by spectral subtraction is presented. It is well known that the spectral subtraction introduces annoying artifacts, which are referred to as undesirable musical noise, in the enhanced speech. The enhancement quality of the spectral subtraction quite depends on the performance of reducing the musical noise. Our approach exploits an adaptive fi...
متن کامل