Quantile based histogram equalization for online applications
نویسندگان
چکیده
The noise robustness of automatic speech recognition systems can be increased by transforming the signal to make the cumulative density functions of the signal’s values in recognition match the ones that where estimated on the training data. This paper describes a real–time online algorithm to approximate the cumulative density functions, after Mel scaled filtering, using a small number of quantiles. Recognition tests where carried out on the Aurora noisy TI digit strings and SpeechDat–Car databases. The average relative reduction of the word error rates was 32% on the noisy TI digit strings and 29% on SpeechDat–Car.
منابع مشابه
High Speed Quantile Based Histogram Equalization
8 In this paper we introduce a new histogram equalization based contrast enhancement method called High Speed Quantile Based Histogram Equalization (HSQHE) suitable for high contrast digital images. The proposed method is an effective tool to deal with the “mean-shift” problem, which is a usual problem with the histogram equalization based contrast enhancement methods. The main idea of HSQHE is...
متن کاملDensity-Based Histogram Partitioning and Local Equalization for Contrast Enhancement of Images
Histogram Equalization technique is one of the basic methods in image contrast enhancement. Using this method, in the case of images with uniform gray levels (with narrow histogram), causes loss of image detail and the natural look of the image. To overcome this problem and to have a better image contrast enhancement, a new two-step method was proposed. In the first step, the image histogram is...
متن کاملCombining neighboring filter channels to improve quantile based histogram equalization
A mismatch between the training data and the test condition of an automatic speech recognition system usually deteriorates the recognition performance. Quantile based histogram equalization can increase the system’s robustness by approximating the cumulative density function of the current signal and then reducing an eventual mismatch based on this estimate. In a first step each output of the m...
متن کاملEvaluation of Quantile Based Histogram Equalization in Combination with Different Root Functions
This paper presents an evaluation of the RWTH large vocabulary speech recognition system on the Aurora 4 noisy Wall Street Journal database. First, the influence of different root functions replacing the logarithm in the feature extraction is studied. Then quantile based histogram equalization is applied, a parametric method to increase the noise robustness by reducing the mismatch between the ...
متن کاملDistribution Regularized Regression Framework for Climate Modeling
Regression-based approaches are widely used in climate modeling to capture the relationship between a climate variable of interest and a set of predictor variables. These approaches are often designed to minimize the overall prediction errors. However, some climate modeling applications emphasize more on fitting the distribution properties of the observed data. For example, histogram equalizati...
متن کامل