• ETRI Journal
• /
• v.38 no.6
• /
• pp.1190-1196
• /
• 2016

We propose a new bandpass filter (BPF)-based online channel normalization method to dynamically suppress channel distortion when the speech and channel noise components are unknown. In this method, an adaptive modulation frequency filter is used to perform channel normalization, whereas conventional modulation filtering methods apply the same filter form to each utterance. In this paper, we only normalize the two mel frequency cepstral coefficients (C0 and C1) with large dynamic ranges; the computational complexity is thus decreased, and channel normalization accuracy is improved. Additionally, to update the filter weights dynamically, we normalize the learning rates using the dimensional power of each frame. Our speech recognition experiments using the proposed BPF-based blind channel normalization method show that this approach effectively removes channel distortion and results in only a minor decline in accuracy when online channel normalization processing is used instead of batch processing

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.3
• /
• pp.155-157
• /
• 2014

In this paper, a novel codebook generation strategy is proposed. With the given codebooks, two codeword selection procedures are proposed and analyzed for generating the quantized multiple-input multiple-output (MIMO) channel state information (CSI). Furthermore, three different quantization and normalization strategies are analyzed. The simulation results suggest that the proposed 'quantized channel generation method 2' is the best strategy to reduce the quantization and normalization errors to generate the final quantized MIMO CSI.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.4
• /
• pp.280-287
• /
• 2016

In this paper, we propose a normalization algorithm that can be applied to adaptive filters for multi-channel active noise control. The FxLMS (Filtered-x Least Mean Square) algorithm for the single-channel active noise control can be normalized in the same way as the NLMS (Normalized Least Mean Square) algorithm, whereas in case of the multi-channel active noise control, the single-channel normalization for the FxLMS algorithm cannot be extended to the normalization for the multi-channel FxLMS algorithm straightforwardly. First, we adopt a generalized normalization algorithm for the multi-channel FxLMS algorithm based on the principle of minimal disturbance and then, proposed a normalized algorithm considering only diagonal elements to avoid computation for matrix inversion. We carried out performance comparisons of the proposed algorithm with other algorithms without normalization. It is shown that the proposed algorithm presents better convergence characteristics under non-stationary environments.

• ETRI Journal
• /
• v.29 no.3
• /
• pp.300-304
• /
• 2007

This paper proposes a new data-driven method for high-pass approaches, which suppresses slow-varying noise components. Conventional high-pass approaches are based on the idea of decorrelating the feature vector sequence, and are trying for adaptability to various conditions. The proposed method is based on temporal local decorrelation using the information-maximization theory for each utterance. This is performed on an utterance-by-utterance basis, which provides an adaptive channel normalization filter for each condition. The performance of the proposed method is evaluated by isolated-word recognition experiments with channel distortion. Experimental results show that the proposed method yields outstanding improvement for channel-distorted speech recognition.

• MALSORI
• /
• no.44
• /
• pp.73-82
• /
• 2002

Channel distortion degrades the performance of speech recognizer in telephone environment. It mainly results from the bandwidth limitation and variation of transmission channel. Variation of channel characteristics is usually represented as baseline shift in the cepstrum domain. Thus undesirable effect of the channel variation can be removed by subtracting the mean from the cepstrum. In this paper, to improve the recognition performance of Korea connected digit telephone speech, channel compensation methods such as CMN (Cepstral Mean Normalization), RTCN (Real Time Cepatral Normalization), MCMN (Modified CMN) and MRTCN (Modified RTCN) are applied to the static MFCC. Both MCMN and MRTCN are obtained from the CMN and RTCN, respectively, using variance normalization in the cepstrum domain. Using HTK v3.1 system, recognition experiments are performed for Korean connected digit telephone speech database released by SITEC (Speech Information Technology & Industry Promotion Center). Experiments have shown that MRTCN gives the best result with recognition rate of 90.11% for connected digit. This corresponds to the performance improvement over MFCC alone by 1.72%, i.e, error reduction rate of 14.82%.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.143-151
• /
• 2012

A new data-driven method for the design of a blind modulation frequency filter that suppresses the slow-varying noise components is proposed. The proposed method is based on the temporal local decorrelation of the feature vector sequence, and is done on an utterance-by-utterance basis. Although the conventional modulation frequency filtering approaches the same form regardless of the task and environment conditions, the proposed method can provide an adaptive modulation frequency filter that outperforms conventional methods for each utterance. In addition, the method ultimately performs channel normalization in a feature domain with applications to log-spectral parameters. The performance was evaluated by speaker-independent isolated-word recognition experiments under additive noise environments. The proposed method achieved outstanding improvement for speech recognition in environments with significant noise and was also effective in a range of feature representations.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.6
• /
• pp.267-271
• /
• 2002

The Hotelling transform is based on statistical properties of an image. The principal uses of this transform are in data compression. The basic concept of the Hotelling transform is that the choice of basis vectors pointing the direction of maximum variance of the data. This property can be used for rotation normalization. Many objects of interest in pattern recognition applications can be easily standardized by performing a rotation normalization that aligns the coordinate axes with the axes of maximum variance of the pixels in the object. However, this transform can not be used to rotation normalization of color images directly. In this paper, we propose a new method for rotation normalization of color images based on the Hotelling transform. The Hotelling transform is performed to calculate basis vectors of each channel. Then the summation of vectors of all channels are processed. Rotation normalization is performed using the result of summation of vectors. Experimental results showed the proposed method can be used for rotation normalization of color images effectively.

• Genomics & Informatics
• /
• v.5 no.3
• /
• pp.118-123
• /
• 2007

The current existing literature offers little guidance on how to decide which method to use to analyze one-channel microarray measurements when dealing with large, grouped samples. Most previous methods have focused on two-channel data;therefore they can not be easily applied to one-channel microarray data. Thus, a more reliable method is required to determine an appropriate combination of individual basic processing steps for a given dataset in order to improve the validity of one-channel expression data analysis. We address key issues in evaluating the effectiveness of basic statistical processing steps of microarray data that can affect the final outcome of gene expression analysis without focusingon the intrinsic data underlying biological interpretation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.1
• /
• pp.168-182
• /
• 2020

Spoofing attacks, especially replay attacks, pose great security challenges to automatic speaker verification (ASV) systems. Current works on replay attacks detection primarily focused on either developing new features or improving classifier performance, ignoring the effects of feature variability, e.g., the channel variability. In this paper, we first establish a mathematical model for replay speech and introduce a method for eliminating the negative interference of the channel. Then a novel feature is proposed to detect the replay attacks. To further boost the detection performance, four post-processing methods using normalization techniques are investigated. We evaluate our proposed method on the ASVspoof 2017 dataset. The experimental results show that our approach outperforms the competing methods in terms of detection accuracy. More interestingly, we find that the proposed normalization strategy could also improve the performance of the existing algorithms.

• Journal of Broadcast Engineering
• /
• v.20 no.5
• /
• pp.738-747
• /
• 2015

It is difficult to use a recognition algorithm of an image in a foggy environment because the color and edge information is removed. One of the famous defogging algorithm is haze removal by using 'Dark Channel Prior(DCP)' which is used to predict for transmission rate using color information of an image and eliminates fog from the image. However, in case that the image has factors such as sunset or yellow dust, there is overemphasized problem on the color of certain channel after haze removal. Furthermore, in case that the image includes an object containing high RGB channel, the transmission related to this area causes a misestimated issue. In this paper, we purpose an enhanced fog elimination algorithm by using improved color normalization and haze rate revision which correct mis-estimation haze area on the basis of color information and edge information of an image. By eliminating the color distortion, we can obtain more natural clean image from the haze image.