• Speech Sciences
• /
• v.15 no.4
• /
• 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.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• 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.

• Proceedings of the KSPS conference
• /
• 2005.11a
• /
• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.6
• /
• pp.26-33
• /
• 2001

Though speaker recognition based on conventional AR HMM shows good performance, its lack of modeling the environmental noise makes its performance degraded in case of practical noisy environment. In this paper, a robust speaker recognition system based on AR HMM is proposed, where noise is considered in the observation signal model for practical noisy environment and duration-term is considered to increase performance. Experimental results, using the digits database from 100 speakers (77 males and 23 females) under white noise and car noise, show improved performance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.607-610
• /
• 2021

When learning a model in supervised learning, input data and the label of the data are required. However, labeling is high cost task and if automated, there is no guarantee that the label will always be correct. In the case of supervised learning in such a noisy labels environment, the accuracy of the model increases at the initial stage of learning, but decrease significantly after a certain period of time. There are various methods to solve the noisy label problem. But in most cases, the probability predicted by the model is used as the pseudo label. So, we proposed a method to predict the true label more quickly by refining the probabilities predicted by the model. Result of experiments on the same environment and dataset, it was confirmed that the performance improved and converged faster. Through this, it can be applied to methods that use the probability distribution predicted by the model among existing studies. And it is possible to reduce the time required for learning because it can converge faster in the same environment.

• Journal of Navigation and Port Research
• /
• v.30 no.5 s.111
• /
• pp.343-349
• /
• 2006

In order to enhance the robustness against noisy environment, the previous GPS initial synchronization method of DGPS reference stations adopts not only the coherent integration method but also the non-coherent integration method. However the previous GPS initial synchronization method muses the non-coherent integration loss, which is a dominant factor among the signal acquisition losses in noisy environment. And the non-coherent integration loss increases with the strength of noise signal. In this paper, a novel GPS initial synchronization method is proposed for robust DGPS reference stations in noisy environment. This paper presents that the proposed GPS initial synchronization method suppresses the non-coherent acquisition loss. Furthermore, with regard to the mean acquisition time, it is shown that the number of the search cells of the proposed GPS initial synchronization method is much smaller than that of the previous GPS initial synchronization method Finally, through the simulation by the GPS simulator, it is seen that the GPS signal of nigh signal-to-noise ratio can be acquired under increased noise floor using the proposed GPS initial synchronization method.

• Journal of information and communication convergence engineering
• /
• v.1 no.4
• /
• 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.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.7 no.4
• /
• 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.

• The Journal of Korea Robotics Society
• /
• v.6 no.2
• /
• 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.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06a
• /
• 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.