Speech recognition in noisy environments is a very difficult task. It is is desirable to search for parameters that would relate the speech enhancement technique directly with the recognizer to optimize the recognition performance. In this paper, Noise Reduction Rate (NRR) and Mel Cepstrum Distortion (MelCD) are investigated when using Spectral Subtraction (SS). Under low SNR such as 0dB,5dB an...

Elimination of additive noise from a speech signal is a fundamental problem in audio signal processing. In this paper we restrict our considerations to the case where only a single microphone recording of the noisy signal is available. The algorithms which we investigate proceed in two steps: First, the noise power spectrum is estimated. A method based on temporal quantiles in the power spectra...

This paper proposes a method of noise reduction by pairedmicrophones as a front-end processor for speech recognition systems. This method estimates noises using a subtractive microphone array and subtracts them from the noisy speech signal using the Spectral Subtraction (SS). Since this method can estimate noises analytically and frame by frame, it is easy to estimate noises not depending on th...

This paper describes a spatial spectral subtraction method by using the complementary beamforming microphone array to enhance noisy speech signals for speech recognition. The complementary beamforming is based on two types of beamformers designed to obtain complementary directivity patterns with respect to each other. In this paper, it is shown that the nonlinear subtraction processing with com...

Spectral subtraction has the drawback that it introduces an unpleasant residual noise. This noise is a result of under-subtraction which occurs due to high variance of noise magnitude spectrum estimates. In this study we investigate a number of smoothing techniques that can be employed to reduce this variability. We extend the scope of this paper by using the phase spectrum in a novel manner al...

A new technique for the modelling of perceptual systems called formal modelling is developed. This technique begins with qualitative observations about the perceptual system, the so-called perceptual symmetries, to obtain through mathematical analysis certain model structures which may then be calibrated by experiment. The analysis proceeds in two different ways depending upon the choice of lin...

Automatic speech recognition performance degrades significantly when speech is affected by environmental noise. Nowadays, the major challenge is to achieve good robustness in adverse noisy conditions so that automatic speech recognizers can be used in real situations. Spectral subtraction (SS) is a well-known and effective approach; it was originally designed for improving the quality of speech...

Spectral Subtraction (SS), as a speech enhancement technique, originally designed for improving quality of speech signal judged by human listeners. it usually improve the quality and intelligibility of speech signals, while the speech recognition systems need compensation techniques capable of reducing the mismatch between the noisy speech features and the clean models. This paper proposes a no...

A new monaural method for the suppression of late room reverberation from speech signals, based on spectral subtraction, is presented. The problem of reverberation suppression differs from classical speech de-noising in that the “reverberation noise” is non stationary. In this paper, the use of a novel estimator of the non-stationary reverberationnoise power spectrum, based on a statistical mod...

The handsfree mode is convenient when using a mobile phone in a vehicle. This mode brings the microphone away from the talker’s mouth. As a consequence the speech signal picked up has low Signal to Noise Ratio. Thus, to improve the SNR a noise reduction method is employed. The proposed method is an improvement of the well-known spectral subtraction method which uses one SNR-dependent gain funct...