Mean And Variance Normalization Research Articles

심층신경망 기반의 음성인식을 위한 절충된 특징 정규화 방식*

Feature normalization is a method to reduce the effect of environmental mismatch between the training and test conditions through the normalization of statistical characteristics of acoustic feature parameters. It demonstrates excellent performance improvement in the traditional Gaussian mixture model-hidden Markov model (GMM-HMM)-based speech recognition system. However, in a deep neural network (DNN)-based speech recognition system, minimizing the effects of environmental mismatch does not necessarily lead to the best performance improvement. In this paper, we attribute the cause of this phenomenon to information loss due to excessive feature normalization. We investigate whether there is a feature normalization method that maximizes the speech recognition performance by properly reducing the impact of environmental mismatch, while preserving useful information for training acoustic models. To this end, we introduce the mean and exponentiated variance normalization (MEVN), which is a compromise between the mean normalization (MN) and the mean and variance normalization (MVN), and compare the performance of DNN-based speech recognition system in noisy and reverberant environments according to the degree of variance normalization. Experimental results reveal that a slight performance improvement is obtained with the MEVN over the MN and the MVN, depending on the degree of variance normalization.

Employing Robust Principal Component Analysis for Noise-Robust Speech Feature Extraction in Automatic Speech Recognition with the Structure of a Deep Neural Network

In recent decades, researchers have been focused on developing noise-robust methods in order to compensate for noise effects in automatic speech recognition (ASR) systems and enhance their performance. In this paper, we propose a feature-based noise-robust method that employs a novel data analysis technique—robust principal component analysis (RPCA). In the proposed scenario, RPCA is employed to process a noise-corrupted speech feature matrix, and the obtained sparse partition is shown to reveal speech-dominant characteristics. One apparent advantage of using RPCA for enhancing noise robustness is that no prior knowledge about the noise is required. The proposed RPCA-based method is evaluated with the Aurora-4 database and a task using a state-of-the-art deep neural network (DNN) architecture as the acoustic models. The evaluation results indicate that the newly proposed method can provide the original speech feature with significant recognition accuracy improvement, and can be cascaded with mean normalization (MN), mean and variance normalization (MVN), and relative spectral (RASTA)—three well-known and widely used feature robustness algorithms—to achieve better performance compared with the individual component method.

Histogram equalization using a reduced feature set of background speakers’ utterances for speaker recognition

We propose a method for histogram equalization using supplement sets to improve the performance of speaker recognition when the training and test utterances are very short. The supplement sets are derived using outputs of selection or clustering algorithms from the background speakers’ utterances. The proposed approach is used as a feature normalization method for building histograms when there are insufficient input utterance samples. In addition, the proposed method is used as an i-vector normalization method in an i-vector-based probabilistic linear discriminant analysis (PLDA) system, which is the current state-of-the-art for speaker verification. The ranks of sample values for histogram equalization are estimated in ascending order from both the input utterances and the supplement set. New ranks are obtained by computing the sum of different kinds of ranks. Subsequently, the proposed method determines the cumulative distribution function of the test utterance using the newly defined ranks. The proposed method is compared with conventional feature normalization methods, such as cepstral mean normalization (CMN), cepstral mean and variance normalization (MVN), histogram equalization (HEQ), and the European Telecommunications Standards Institute (ETSI) advanced front-end methods. In addition, performance is compared for a case in which the greedy selection algorithm is used with fuzzy C-means and K-means algorithms. The YOHO and Electronics and Telecommunications Research Institute (ETRI) databases are used in an evaluation in the feature space. The test sets are simulated by the Opus VoIP codec. We also use the 2008 National Institute of Standards and Technology (NIST) speaker recognition evaluation (SRE) corpus for the i-vector system. The results of the experimental evaluation demonstrate that the average system performance is improved when the proposed method is used, compared to the conventional feature normalization methods.

Histogram Equalization Using Centroids of Fuzzy C-Means of Background Speakers’ Utterances for Majority Voting Based Speaker Identification

이전 연구에서 퍼지 C-Means의 중심 데이터로 이루어진 보조 데이터를 이용한 히스토그램 등화기법을 제안하였다. 보조 데이터를 이용한 히스토그램 등화기법은 사용하는 참조 집합의 크기에 따라 화자 식별 성능에 영향을 받는다. 그러나 인식 시점에서 최적의 파라미터를 찾기는 어렵다. 이 문제를 해결하기 위해 본 논문에서는 화자 식별을 위한 다수 투표 방식에 기반을 둔 보조 데이터를 이용한 히스토그램 등화기법을 제안한다. 다수 투표 기반의 제안한 방법은 여러 종류의 보조 데이터를 이용한 히스토그램 등화기법으로 입력 음성을 분류한다. 본 연구에서 제안한 방법을 CMN(Cepstral Mean Normalization), MVN(Mean and Variance Normalization), HEQ(Histogram Equalization)와 같은 기존의 특징 정규화 방법 및 보조 데이터를 이용한 히스토그램 등화기법과 비교한다. In a previous work, we proposed a novel approach of histogram equalization using a supplement set which is composed of centroids of Fuzzy C-Means of the background utterances. The performance of the proposed method is affected by the size of the supplement set, but it is difficult to find the best size at the point of recognition. In this paper, we propose a histogram equalization using a supplement set for majority voting based speaker identification. The proposed method identifies test utterances using a majority voting on the histogram equalization methods with various sizes of supplement sets. The proposed method is compared with the conventional feature normalization methods such as CMN(Cepstral Mean Normalization), MVN(Mean and Variance Normalization), and HEQ(Histogram Equalization) and the histogram equalization method using a supplement set.

Enhancing the magnitude spectrum of speech features for robust speech recognition

In this article, we present an effective compensation scheme to improve noise robustness for the spectra of speech signals. In this compensation scheme, called magnitude spectrum enhancement (MSE), a voice activity detection (VAD) process is performed on the frame sequence of the utterance. The magnitude spectra of non-speech frames are then reduced while those of speech frames are amplified. In experiments conducted on the Aurora-2 noisy digits database, MSE achieves an error reduction rate of nearly 42% relative to baseline processing. This method outperforms well-known spectral-domain speech enhancement techniques, including spectral subtraction (SS) and Wiener filtering (WF). In addition, the proposed MSE can be integrated with cepstral-domain robustness methods, such as mean and variance normalization (MVN) and histogram normalization (HEQ), to achieve further improvements in recognition accuracy under noise-corrupted environments.

Combination of SPLICE and Feature Normalization for Noise Robust Speech Recognition

It is well-known that the performance of automatic speech recognition (ASR) systems are easily affected by acoustic mismatch between training and testing conditions. This mismatch is often caused by various kinds of environmental noise or distortion. To reduce the effect of mismatch, feature normalization, feature enhancement, model adaptation, etc. have been studied intensively. Cepstral mean normalization (CMN), mean and variance normalization (MVN) and histogram equalization (HEQ) are well-known methods of feature normalization. Stereo-based piecewise linear compensation for environments (SPLICE) is one of the feature enhancement methods. In this paper, we describe how to combine these methods to effectively improve the robustness of ASR systems. In the experiments performed on the Aurora-2 database, a good combination showed a 41% improvement in word error rate over SPLICE only, and a 25% improvement over the conventional combination of SPLICE and CMN.

Subband Feature Statistics Normalization Techniques Based on a Discrete Wavelet Transform for Robust Speech Recognition

This letter proposes a novel scheme that applies feature statistics normalization techniques for robust speech recognition. In the proposed approach, the processed temporal-domain feature sequence is first decomposed into nonuniform subbands using the discrete wavelet transform (DWT), and then each subband stream is individually processed by well-known normalization methods, such as mean and variance normalization (MVN) and histogram equalization (HEQ). Finally, we reconstruct the feature stream with all of the modified subband streams using the inverse DWT. With this process, the components that correspond to more important modulation spectral bands in the feature sequence can be processed separately.