• 음성과학
• /
• 제15권4호
• /
• pp.85-96
• /
• 2008

Automatic speech recognition has severe performance degradation under noisy environments. To cope with the noise problem, many methods have been proposed. Most of them focused on noise-robust features or model adaptation. However, researchers have overlooked utterance verification (UV) under noisy environments. In this paper we discuss UV problems based on the normalized confidence measure. First, we show that UV performance is also degraded in noisy environments with the experiments of an isolated word recognition. Then we observe how the degradation of UV performances is suffered. Based on the UV experiments we propose a modeling method of the statistics of phone confidences using sigmoid functions. For obtaining the parameters of the sigmoidal models, the particle swarm optimization (PSO) is adopted. The proposed method improves 20% rejection performance. Our experimental results show that the PSO-NCM can apply noise speech recognition successfully.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1392-1394
• /
• 1996

This paper presents an algorithm to separate vowels from consonants in Korean characters captured in noisy images and to recognize them. The algorithm has been originally developed for the recognition of the usage code (which is represented by a single Korean character) in the license plates or Korean vehicles. It, however, could be easily adopted to other applications with minor changes, in which character recognition is needed and the environment is noisy. The key ideas or the algorithm are to localize the vowels utilizing the Hough transformation and to separate the vowels from consonants utilizing mathematical morphology. We observed that the presented algorithm effectively separates vowels even if the vowels and consonants are joined together after thresholding. We also observed that our algorithm outperforms some conventional algorithms especially when the input images are noisy. The details of the comparison study are presented in the paper.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 추계 학술대회 발표논문집
• /
• pp.59-62
• /
• 2005

Voice activity detection (VAD) is important in many areas of speech processing technology. Speech/nonspeech discrimination in noisy environments is a difficult task because the feature parameters used for the VAD are sensitive to the surrounding environments. Thus the VAD performance is severely degraded at low signal-to-noise ratios (SNRs). In this paper, a new VAD algorithm is proposed based on the degree of voicing and Quantile SNR (QSNR). These two feature parameters are more robust than other features such as energy and spectral entropy in noisy environments. The effectiveness of proposed algorithm is evaluated under the diverse noisy environments in the Aurora2 DB. According to out experiment, the proposed VAD outperforms the ETSI Advanced Frontend VAD.

• 한국음향학회지
• /
• 제20권6호
• /
• pp.26-33
• /
• 2001

기존의 AR HMM(auroreg ressive hidden morkov model)에 의한 화자인식 방법은 그 성능이 우수하나, 잡음에 대한 것이 고려되지 않아 실제 환경에 적용시 성능저하가 문제가 된다. 본 논문에서는 실제 환경에 맞추기 위하여 관측 신호 모델에서 잡음을 고려하고, 화자인식 성능을 개선하고자 지속시간항 (duration-term)을 포함하는 AR HMM을 이용하여 잡음환경에서의 강인한 화자인식 시스템을 제안한다. 100명의 화자 (남자 77명, 여자 23명)가 2주에 걸쳐 6번 발성한 숫자음 데이터베이스을 가지고, 백색잡음 및 자동차 잡음하에서 실험한 결과, 제안된 방법으로 성능이 향상됨을 확인하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.607-610
• /
• 2021

지도학습에서 모델을 학습함에 있어 입력 데이터와 해당 데이터의 라벨이 필요하다. 하지만 신뢰성 있는 라벨링은 비용과 시간적인 면에서 많이 소요되며 이를 자동화할 경우 라벨이 언제나 맞는다는 보장이 없어 노이즈가 들어가게 된다. 이러한 라벨 노이즈 환경에서 지도학습을 진행할 경우 모델은 학습 초기에는 정확도가 올라가지만, 어느 정도 학습 후 정확도가 크게 감소되는 경향을 보인다. 라벨 노이즈 문제를 해결하기 위해 다양한 방법이 있지만, 대다수의 경우 모델이 예측한 확률을 수도라벨로 사용해 이용하는 경우가 많다. 여기에 대해서 우리는 모델이 예측한 확률을 정제하여 좀 더 빠르게 참 라벨을 예측하는 방법을 제시한다. 기존의 논문 중 모델이 예측한 확률을 사용하는 방법에 우리가 제안하는 방법을 적용하여 같은 환경, 데이터셋에 대해 실험을 진행한 결과 성능개선과 더 빠르게 수렴하는 것을 확인할 수 있었다. 이를 통해 기존 연구들 중 모델이 예측하는 확률분포를 사용하는 방법들에 적용할 수 있고 같은 환경에서도 더 빠르게 수렴시킬 수 있기에 학습 소요시간을 줄일 수 있다.

• 한국항해항만학회지
• /
• 제30권5호
• /
• pp.343-349
• /
• 2006

기존 DGPS 기준국용 GPS 수신기의 초기동기 방법은 잡음환경에 대한 강건성 향상을 위해 동기 누적 기법과 비동기 누적 기법을 함께 이용하고 있다. 그러나, 기존 DGP통 기준국용 GPS 초기동기 방법은 잡음환경에서 발생하는 신호획득 손실 중에서 우세한 성분인 비동기 누적 손실이 발생할 뿐만 아니라 잡음세기가 커질수록 비동기 누적 손실도 커지는 문제가 있다. 본 논문에서는 잡음환경에 강인한 DGPS 기준국을 위해 기존 GPS 초기동기의 비동기 누적 손실 문제를 해결한 새로운 GPS 초기동기 방법을 제안하고, 제안하는 GPS 초기동기 방법이 비동기 누적 손실을 억제하는 효과가 있음을 보인다. 그리고, 평균 초기동기 획득시간 측면에서 제안하는 GPS 초기동기 방법이 기존 GPS 초기동기 방법이 검색해야 할 셀의 개수 보다 더 적은 셀을 검색하는 이점이 있음을 보인다. 마지막으로 GPS 시뮬레이터를 이용한 모의실험을 통해 제안하는 GPS 초기동기 방법이 잡음세기가 증가한 환경에서 높은 신호대 잡음비로 GPS 신호를 획득할 수 있음을 확인한다.

• Journal of information and communication convergence engineering
• /
• 제1권4호
• /
• pp.205-208
• /
• 2003

Voice activity detection is a important problem in the speech recognition and speech communication. This paper introduces new feature parameter which are reconstructed by spectral entropy of information theory for robust voice activity detection in the noise environment, then analyzes and compares it with energy method of voice activity detection and performance. In experiments, we confirmed that spectral entropy and its reconstructed parameter are superior than the energy method for robust voice activity detection in the various noise environment.

• 한국생산제조학회지
• /
• 제7권4호
• /
• pp.35-41
• /
• 1998

The workplace noise environment is composed of three basic elements : manufacturing (in a generic sense) facilities, office areas, and the community around the facility. Work must be done by all employees , and this involves communication within a variety of locations within the facility ; areas may be extremely noisy, moderately noisy, or quiet, such as an office. At the same time, the facility should not be annoying to the community. In this paper, the workplace environmental noise of office areas in power plant are studied. Turbine generator in power plant generates the noise of 90∼95 dB(A) in the frequency range of 1 kHz, which may cause occupational hearing loss. By abatement method which are made of isolation material and distance damping effect, about 29.5 dB(A) reduction has been obtained in office areas of the Power Plant . But, the workplace environmental noise of office areas in the power plant is not suited to office's purpose.

• 로봇학회논문지
• /
• 제6권2호
• /
• pp.189-196
• /
• 2011

This paper presents a method of topological modeling using only low-cost sonar sensors. The proposed method constructs a topological model by extracting sub-regions from the local grid map. The extracted sub-regions are considered as nodes in the topological model, and the corresponding edges are generated according to the connectivity between two sub-regions. A grid confidence for each occupied grid is evaluated to obtain reliable regions in the local grid map by filtering out noisy data. Moreover, a convexity measure is used to extract sub-regions automatically. Through these processes, the topological model is constructed without predefining the number of sub-regions in advance and the proposed method guarantees the convexity of extracted sub-regions. Unlike previous topological modeling methods which are appropriate to the corridor-like environment, the proposed method can give a reliable topological modeling in a home environment even under the noisy sonar data. The performance of the proposed method is verified by experimental results in a real home environment.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 FIFTH WESTERN PACIFIC REGIONAL ACOUSTICS CONFERENCE SEOUL KOREA
• /
• pp.1015-1020
• /
• 1994

This paper presents the Korean digit recognition method under noise environment using the spectral mapping training based on static supervised adaptation algorithm. In the presented recognition method, as a result of spectral mapping from one space of noisy speech spectrum to another space of speech spectrum without noise, spectral distortion of noisy speech is improved, and the recognition rate is higher than that of the conventional method using VQ and DTW without noise processing, and even when SNR level is 0 dB, the recognition rate is 10 times of that using the conventional method. It has been confirmed that the spectral mapping training has an ability to improve the recognition performance for speech in noise environment.