• Journal of Korea Multimedia Society
• /
• v.4 no.4
• /
• pp.306-315
• /
• 2001

In noise reduction method from noisy speech for speech recognition in noisy environments, conventional spectral subtraction method has a disadvantage which distinction of noise and speech is difficult, and characteristic of noise can't be estimated accurately. Also, noise reduction method in the wavelet transform domain has a disadvantage which loss of signal is generated in the high frequency domain. In order to compensate theme disadvantage, this paper propose spectral subtraction method in continuous wavelet transform domain which speech and non- speech intervals is distinguished by standard deviation of wavelet coefficient, and signal is divided three scales at different scale. The proposed method extract accurately characteristic of noise in order to apply spectral subtraction method by end detection and band division. The proposed method shows better performance than noise reduction method using conventional spectral subtraction and wavelet transform from viewpoint signal to noise ratio and Itakura-Saito distance by experimental.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.6
• /
• pp.53-61
• /
• 2000

In the speech recognition under the noisy environments, reducing the mismatch introduced between training and testing environments is an important issue. Spectral subtraction is widely used technique because of its simplicity and relatively good performance in noisy environments. In this paper, we introduce histogram method as a reliable noise estimation approach for spectral subtraction. This method has advantages over the conventional noise estimation methods in that it does not need to detect non-speech intervals and it can estimate the noise spectra even in time-varying noise environments. Even though spectral subtraction is performed using a reliable average noise spectrum by the histogram method, considerable amount of residual noise remains due to the variations of instantaneous noise spectrum about mean. To overcome this limitation, we propose a new over-estimation technique based on distribution characteristics of histogram used for noise estimation. Since the proposed technique decides the degree of over-estimation adaptively according to the measured noise distribution, it has advantages to be few the influence of the SNR variation on the noise levels. According to speaker-independent isolated word recognition experiments in car noise environment under various SNR conditions, the proposed histogram-based over-estimation technique outperforms the conventional over-estimation technique.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.4
• /
• pp.817-822
• /
• 2011

This paper first proposes the speech recognition algorithm by detection of the speech and noise sections at each frame using a neural network training by back-propagation algorithm, then proposes the spectral subtraction method which removes the noises at each frame according to detection of the speech and noise sections. In this experiment, the performance of the proposed recognition system was evaluated based on the recognition rate using various speeches that are degraded by white noise and car noise. Moreover, experimental results of the noise reduction by the spectral subtraction method demonstrate using the speech and noise sections detecting by the speech recognition algorithm at each frame. Based on measuring signal-to-noise ratio, experiments confirm that the proposed algorithm is effective for the speech by corrupted the noise using signal-to-noise ratio.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.1
• /
• pp.38-44
• /
• 1999

In this paper, a new spectral subtraction technique with two microphone inputs is proposed. In conventional spectral subtraction using a single microphone, the averaged noise spectrum is subtracted from the observed short-time input spectrum. This results in reduction of mean value of noise spectrum only, the component varying around the mean value remaining intact. In the method proposed in this paper, the short-time noise spectrum excluding the speech component is estimated by introducing the blocking matrix used in Griffiths-Jim-type adaptive beamformer with two microphone inputs, combined with the spectral compensation technique. A simulation was conducted to verify the effectiveness of the method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.6
• /
• pp.1946-1963
• /
• 2014

Most background subtraction methods focus on dynamic and complex scenes without considering robustness against noise. This paper proposes a background subtraction algorithm based on dictionary learning and sparse coding for handling low light conditions. The proposed method formulates background modeling as the linear and sparse combination of atoms in the dictionary. The background subtraction is considered as the difference between sparse representations of the current frame and the background model. Assuming that the projection of the noise over the dictionary is irregular and random guarantees the adaptability of the approach in large noisy scenes. Experimental results divided in simulated large noise and realistic low light conditions show the promising robustness of the proposed approach compared with other competing methods.

• Speech Sciences
• /
• v.11 no.1
• /
• pp.7-20
• /
• 2004

In this paper, we propose a two-step noise compensation algorithm in feature extraction for achieving robust speech recognition. The proposed method frees us from requiring a priori information on noisy environments and is simple to implement. First, in frequency domain, the Harmonics-based Spectral Subtraction (HSS) is applied so that it reduces the additive background noise and makes the shape of harmonics in speech spectrum more pronounced. We then apply a judiciously weighted variance Feature Vector Normalization (FVN) to compensate for both the channel distortion and additive noise. The weighted variance FVN compensates for the variance mismatch in both the speech and the non-speech regions respectively. Representative performance evaluation using Aurora 2 database shows that the proposed method yields 27.18% relative improvement in accuracy under a multi-noise training task and 57.94% relative improvement under a clean training task.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.262-266
• /
• 1998

In the speech recognition under the noisy environments, reducing the mismatch introduced between training and testing environments is an important issue, and spectral subtraction is widely used technique because of its simplicity and relatively good performance in noisy environments. In this paper, we introduced histogram method as a reliable noise estimationi approach for spectral subtraction. To deal with the problem of residual noise after spectral subtraction, we proposed a new ove-estimation technique based on distribution characteristics of histogram used for noise estimation. Since the proposed technique decides the degree of over-estimation adaptively according to the measured noise distribution, it can cope with the SNR variations effectively in compared with the conventional over-estimation technique.

• Journal of Korea Multimedia Society
• /
• v.4 no.1
• /
• pp.56-66
• /
• 2001

The spectral subtraction algorithm using a criterion based on the human perception has been recently developed. The speech processed with Virag's algorithm sounds more pleasant to a human listener than those obtained by the classical methods. However, Virag's algorithm requires a robust voice activity detector (VAD). In the ESS (extended spectral subtraction) algorithm without VAD, the residual noise becomes more noticeable as the SNR decrease. In this paper we propose a new speech enhancement method, the combination of Wiener filter and spectral subtraction based on noise masking characteristics in the human auditory system. There is no need of VAD because the noise can be successively updated even during speech activity using Wiener filter. The adjustment of the subtraction parameter based on the masking threshold makes the residual noise inaudible. The proposed method has been compared with conventional spectral subtraction algorithms. Objective and subjective evaluation of the proposed system is performed with several noise types having different time-frequency distributions. The application of objective measures, the study of the speech spectrograms, as well as subjective listening tests, confirm that the enhanced speech with proposed algorithm is more pleasant to a human listener.

• The Journal of Engineering Research
• /
• v.3 no.1
• /
• pp.43-46
• /
• 1998

Considerable research in the last three decades has examined the problem of enhancement of speech degraded by additive background noise. We compare traditional methods such as spectral subtraction and Wiener filter, recently proposed psychoacoustic model based methods such as perceptual filter and noise suppression in EVRC in terms of performance and complexity.

• The Journal of the Acoustical Society of Korea
• /
• v.11 no.2
• /
• pp.73-84
• /
• 1992

This paper studies noise subtraction methods and distance measures for speech recognition in a noisy environment, and investigates noise robustness of the distance measures applied to the problem of isolated word recognition in white Gaussian and colored noise (vehicle noise) environments. Noise subtraction methods which can be used as a pre-processor for the speech recognition system, such as the spectral subtraction method, autocorrelation subtraction method, adaptive noise cancellation and acoustic beamforming are studied, and distance measures such and Log Likelihood Ratio ($d_{LLR}$), cepstral distance measure ($d_{CEP}$), weighted cepstral distance measure ($d_{WCEP}$), spectral slope distance measure ($d_{RPS}$) and cepstral projection distance measure ($d_{CP},\;d_{BCP},\;d_{WCP},\;d_{BWCP}$) are also investigated. Testing of the distance measures for speaker-dependent isolated word recognition in a noisy environment indicate that $d_{RPS}\;and\;d_{WCEP}$ which weigh higher order cepstral coefficients more heavily give considerable performance improvement over $d_{CEP}and\;d_{LLR}$. In addition, when no pre-emphasis is performed, the recognizer can maintain higher performance under high noise conditions.