• 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 Broadcast Engineering
• /
• v.9 no.1
• /
• pp.9-16
• /
• 2004

In this paper, we present a speech enhancement method as a pre-processor for voice commander under car environment. For the friendly and safe use of voice commander in a running car, non-stationary audio signals such as music and non-candidate speech should be reduced. Ow technique is a two microphone-based one. It consists of two parts Blind Source Separation (BSS) and Kalman filtering. Firstly, BSS is operated as a spatial filter to deal with non-stationary signals and then car noise is reduced by kalman filtering as a temporal filter. Algorithm Performance is tested for speech recognition. And the results show that our two microphone-based technique can be a good candidate to a voice commander.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.7
• /
• pp.1069-1076
• /
• 2012

We use largely two methods, how to control the noise of the KTX, they are the passive noise control method and the active noise control method. The passive noise control has been used in a variety of ways since the KTX opening day, but lately it has shown the technical limitations by being dropped sharply. So, it is getting important to conduct the research about ANC that is able to reduce the ambient noise when the environmental-factor changes and be installed easily. To reduce a three-dimensional closed-space sound field like a car of a high-speed rail is hard to do using single channel ANC control system. Therefore we have to model the paths of the noise exactly for reducing the noise. And the control speakers and the error mics should be designed for optimal position. In this paper, we designed the transfer functions for modeling the noise paths under the influence of the distance between control speakers & error mics and primary noise speaker in TEST-BED where there is modeled as actual interior of KTX. We have made the modeling and the simulations of interior environment of KTX car by using three frequency bands of 120Hz, 280Hz, 360Hz. After the modeling, we compared the performance of active noise control and also we analyzed what to affect with difference in distance. After comparing of the performance using Pure Tone 120Hz, 280Hz, 360Hz at each modeling and then we simulated ANC for KTX's interior noise which we measured really and analyzed.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.26 no.6_spc
• /
• pp.729-735
• /
• 2016

According to the survey for working environment of the cashiers in highway tollbooths, workers replied that noise was the most harmful substances next to air pollutant in the tollbooth. Researches on the noise levels exposed to cashiers in the highway tollbooth scarcely have been performed. Therefore, the aim of this study was to acquire baseline data to prevent health impairments of the cashiers by evaluating noise level exposed to them. Noise dosimeters were used for monitoring workers' noise exposure level in the tollbooths at 8 different highway tollgates. The noise levels of tollbooths did not exceed noise exposure limit of the ministry of labor, 90 dB(A). The average TWA inside of the tollbooths was 55.4 dB(A) and the average TWA outside of tollbooths was 58.3 dB(A). The average TWA outside of tollbooths was slightly higher than that of inside of tollbooths. However, the significance probability(p-value) was 0.255 which means statistically not significant. The noise levels inside and outside of tollbooth were statistically significant to both mean traffic volume per day and traffic volume of passenger car.

• Journal of Digital Convergence
• /
• v.13 no.10
• /
• pp.313-318
• /
• 2015

A traditional speech enhancement methods distort the sound spectrum generated according to estimation of the remaining noise, or invalid noise is a problem of lowering the speech recognition performance. In this paper, we propose a speech detection method that convergence the sound energy distribution process and sound energy parameters. The proposed method was used to receive properties reduce the influence of noise to maximize voice energy. In addition, the smaller value from the feature parameters of the speech signal The log energy features of the interval having a more of the log energy value relative to the region having a large energy similar to the log energy feature of the size of the voice signal containing the noise which reducing the mismatch of the training and the recognition environment recognition experiments Results confirmed that the improved recognition performance are checked compared to the conventional method. Car noise environment of Pause Hit Rate is in the 0dB and 5dB lower SNR region showed an accuracy of 97.1% and 97.3% in the high SNR region 10dB and 15dB 98.3%, showed an accuracy of 98.6%.

• 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.

• The Journal of the Korea Contents Association
• /
• v.9 no.1
• /
• pp.139-146
• /
• 2009

This paper addresses a modified spectral subtraction schemes which is suitable to speech recognition under low signal-to-noise ratio (SNR) noisy environment such as the automatic speech recognition (ASR) system in car. The conventional spectral subtraction schemes rely on the SNR such that attenuation is imposed on that part of the spectrum that appears to have low SNR, and accentuation is made on that part of high SNR. However, such postulation is adequate for high SNR environment, it is grossly inadequate for low SNR scenarios such as that of car environment. Proposed methods focused specifically to low SNR noisy environment by using weighting function for enhancing speech dominant region in speech spectrum. Experimental results by using voice commands for car show the superior performance of the proposed method over conventional methods.

• Journal of KSNVE
• /
• v.7 no.4
• /
• pp.701-708
• /
• 1997

Up to now, numerical methods such as Finite Element Method(FEM) or Boundary Element Method(BEM) have been widely used to find the optimized resonator's position during designing a car intake system. However, these methods are not useful at the first stage of car design since it is not easy to change a numerical model consist of a large mesh size. A software has been developed to cover the defects using 4-pole parameter method. The software is running at Windows 95 environment for a user's convenience. To show its usefulness, it is applied to a real automobile intake system.

• Speech Sciences
• /
• v.15 no.1
• /
• pp.75-83
• /
• 2008

The interior of an automobile is a very noisy environment with both stationary cruising noise and the reverberated music or speech coming out from the audio system. For robust speech recognition in a car environment, it is necessary to extract a driver's voice command well by removing those background noises. Since we can handle the music and speech signals from an audio system in a car, the reverberated music and speech sounds can be removed using an acoustic echo canceller. In this paper, we implement an acoustic echo canceller with robust double-talk detection algorithm using TMS-320C6711 DSK. First we developed the echo canceller on the PC for verifying the performance of echo cancellation, then implemented it on the TMS320C6711 DSK. For processing of one speech sample with 8kHz sampling rate and 256 filter taps of the echo canceller, the implemented system used only 0.035ms and achieved the ERLE of 20.73dB.

• Phonetics and Speech Sciences
• /
• v.5 no.2
• /
• pp.93-97
• /
• 2013

This paper is on designing an indoor driving simulator to evaluate the performance of in-car speech recognizer when influenced by the elements, which lower the success rate of speech recognition. The proposed simulator simulates vehicle noise which was pre-recorded in diverse driving environments and driver's speech. Additionally, the proposed Lombard effect conversion module in this simulator enables the speech recorded in a studio environment to convert into various possible driving scenarios. The relevant experimental results have confirmed that the proposed simulator is a feasible approach for realizing an effective method as it achieved similar speech recognition results to the real driving environment.