• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.69-72
• /
• 2003

본 논문에서는 범용 DSP를 이용한 잡음환경에 강인한 음성인식 시스템을 구현하였다. 구현된 시스템은 TI사의 범용 DSP인 TMS320C32를 이용하였고, 실시간 음성 입력을 위한 음성 Codec과 외부 인터페이스를 확장하여 인식결과를 출력하도록 구성하였다. 또한, 기존의 음성 인식 시스템에 사용한 파라메터에 대한 고찰과 ICA를 이용하여 잡음 환경에 강인한 음성 특징 파라메터를 제안하고 성능 비교 실험을 하였다. 제안된 ICA 파라메터를 적용하여 음성인식 시스템을 구현하였다. 그리고, 독립적으로 동작 가능한 음성인식 시스템의 응용 예로 무선자동차에 적용시켜 실험했다.

• The Journal of the Acoustical Society of Korea
• /
• v.17 no.4
• /
• pp.60-66
• /
• 1998

본 연구에서는 임펄스 잡음 환경 하에서, 대표적인 Bussgang계열의 블라인드 등화 알고리즘인 LMS-Sato 및 LMS-CMA 블라인드 등와 알고리즘의 수렴특성을 컴퓨터 모의 실험을 통하여 살펴보았다. LMAD-Sato 및 LMAD-CMA 블라인드 등화 알고리즘을 유도 하고, 동일한 조건하에서 그 수렴특성을 살펴보았다. 16-QAM 데이터에 대한 실험 결과 임 펄스 잡음 환경 하에서 LMAD 형태의 블라인드 등화 알고리즘이 LMS 형태의 블라인드 등 화 알고리즘 보다 안정적인 수렴특성을 보여 주었다. 또한, normalized 형태의 LMAD-Sato 및 CMA 블라인드 등화 알고리즘을 제안하였으며, 실험 결과 이들 알고리즘들이 임펄스 잡 음 환경에서 LMAD 형태의 알고리즘 보다 더 우수한 수렴 특성을 보여 주었다.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.5
• /
• pp.68-75
• /
• 1997

Spectral subtraction is widely-used preprocessing technique for speech recognition in additive noise environments, but it requires a good estimate of the noise power spectrum. In this paper, we employ the histogram technique for the estimation of noise spectrum. This technique has advantages over other noise estimation methods in that it does not requires speech/non-speech detection and can estimate slowly-varying noise spectra. According to the speaker-independent isolated word recognition in both colored Gaussian and car noise environments under various SNR conditions. Histogram-technique-based spectral subtraction method yields superier performance to the one with conventional noise estimation method using the spectral average of initial frames during non-speech period.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.346-349
• /
• 2017

Digital image processing is widely used in a variety of areas, and noise elimination is used as the preprocessing in all the image processing processes. Degradation is occurred in the image data due to multiple reasons. Degradation is to add the noise in the image signal, and salt and pepper noise is the representative one to cause degradation. Therefore, image restoration algorithm was proposed to process with histogram weight filter and median filter by the noise density of local mask to restore the damaged image in the salt and pepper noise environment, in this article. In addition, it was compared with the existing methods using peak signal to noise ratio(PSNR) as the objective determination factor of improvement effect.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.1C
• /
• pp.81-89
• /
• 2003

For improving the performance of noise suppression in tactical communication environments, an enhanced MELP vocoder is suggested, in which an acoustic noise suppressor is integrated into the front end of the MELP algorithm, and an FEC code into the channel side of the MELP algorithm. The acoustic noise suppressor is the modified IS-127 EVRC noise suppressor which is adapted for the MELP vocoder. As for FEC, the turbo code, which consists of rate-113 encoding and BCJR-MAP decoding algorithm, is utilized. In acoustic noise environments, the lower the SNR becomes, the more the effects of noise suppression is increased. Moreover, The suggested system has greater noise suppression effects in stationary noise than in non-stationary noise, and shows its superiority by 0.24 in MOS test to the original MELP vocoder. When the interleave size is one MELP frame, BER 10-6 is accomplished at channel bit SNR 4.2 ㏈. The iteration of decoding at 3 times is suboptimal in its complexity vs. performance. Synthetic quality is realized as more than MOS 2.5 at channel bit SNR 2 ㏈ in subjective voice quality test, when the interleave size is one MELP frame and the iteration of decoding is more than 3 times.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.2
• /
• pp.78-87
• /
• 2006

In this paper. we propose an effective mask estimation scheme for missing-feature reconstruction in order to achieve robust speech recognition under unknown noise environments. In the previous work. colored noise is used for training the mask classifer, which is generated from the entire frequency Partitioned signals. However it gives a limited performance under the restricted number of training database. To reflect the spectral events of more various background noise and improve the performance simultaneously. a new Bayesian classifier for mask estimation is proposed, which works independent of other frequency bands. In the proposed method, we employ the colored noise which is obtained by combining colored noises generated from each frequency band in order to reflect more various noise environments and mitigate the 'sparse' database problem. Combined with the cluster-based missing-feature reconstruction. the performance of the proposed method is evaluated on a task of noisy speech recognition. The results show that the proposed method has improved performance compared to the Previous method under white noise. car noise and background music conditions.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.9
• /
• pp.1673-1678
• /
• 2016

In the area of the speech recognition processing, background noises are caused the incorrect response to the speech input, therefore the speech recognition rates are decreased by the background noises. Accordingly, a more high level noise processing techniques are required since these kinds of noise countermeasures are not simple. Therefore, this paper proposes an algorithm to distinguish between the stationary background noises or non-stationary background noises and the speech signal having short time duration in the noisy environments. The proposed algorithm uses the characteristic parameter of the improved speech signal as an important measure in order to distinguish different types of the background noises and the speech signals. Next, this algorithm estimates various kinds of the background noises using a multi-layer perceptron neural network. In this experiment, it was experimentally clear the estimation of the background noises and the speech signals.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.3
• /
• pp.254-260
• /
• 2019

Recently, the importance of signal processing has become gradually significant, as the frequency of video media increases in various fields. However, numerous kinds of noise generated in the transmission and reception processes can possibly affect the signal information, and the noise removal is for that reason essential as a preprocessing step. In this paper, we propose an algorithm to remove the mixed noise which is composed of impulse noise and AWGN. This algorithm is used for image restoration by noise judgment for efficient noise removal in a complex noise environment, and the noise is removed by considering spatial characteristics and pixel variations. Simulation results show that unlike existing methods, the algorithm has excellent noise cancellation characteristics by minimizing both noise effects and consequently eliminating the mixed noise; for objective judgment, we compared and analyzed the data using PSNR and profile.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.3
• /
• pp.200-208
• /
• 2010

In this work, the minimum statistics (MS) algorithm is combined with the codebook driven short-term predictor parameter estimation (CDSTP) to design a speech enhancement algorithm that is robust against various background noise environments. The MS algorithm functions well for the stationary noise but relatively not for the non-stationary noise. The CDSTP works efficiently for the non-stationary noise, but not for the noise that was not considered in the training stage. Thus, we propose to combine CDSTP and MS. Compared with the single use of MS and CDSTP, the proposed method produces better perceptual evaluation of speech quality (PESQ) score, and especially works excellent for the mixed background noise between stationary and non-stationary noises.

• Journal of Sensor Science and Technology
• /
• v.6 no.6
• /
• pp.458-465
• /
• 1997

In this paper, a theory of the geological magnetic filter for the improvements of the signal to noise ratio of the magnetic detection system has been developed. The geological magnetic filter takes two sequences of magnetic fields measured from the reference sensor and the detector sensor and calculate the correlations between them in the frequency domain. Using the filter, we can remove the coherent noises in the time domain and improve the signal to noise ratio of the magnetic detection system. With the recent developments of the DSP hardware technology the geological magnetic filter can be easily implemented using the digital signal processor. We show the ability of the geological magnetic filter under various circumstances through computer simulations. Numerical simulation results show that geological magnetic filter can excellently remove the sensor misalignment effects and the regular short range local noise as well as it delete the coherent noises.