Javier Ramírez

Efficient voice activity detection algorithms using long-term speech information

Abstract Currently, there are technology barriers inhibiting speech processing systems working under extreme noisy conditions. The emerging applications of speech technology, especially in the fields of wireless communications, digital hearing aids or speech recognition, are examples of such systems and often require a noise reduction technique operating in combination with a precise voice activity detector (VAD). This paper presents a new VAD algorithm for improving speech detection robustness in noisy environments and the performance of speech recognition systems. The algorithm measures the long-term spectral divergence (LTSD) between speech and noise and formulates the speech/non-speech decision rule by comparing the long-term spectral envelope to the average noise spectrum, thus yielding a high discriminating decision rule and minimizing the average number of decision errors. The decision threshold is adapted to the measured noise energy while a controlled hang-over is activated only when the observed signal-to-noise ratio is low. It is shown by conducting an analysis of the speech/non-speech LTSD distributions that using long-term information about speech signals is beneficial for VAD. The proposed algorithm is compared to the most commonly used VADs in the field, in terms of speech/non-speech discrimination and in terms of recognition performance when the VAD is used for an automatic speech recognition system. Experimental results demonstrate a sustained advantage over standard VADs such as G.729 and adaptive multi-rate (AMR) which were used as a reference, and over the VADs of the advanced front-end for distributed speech recognition.

Statistical voice activity detection using a multiple observation likelihood ratio test

Currently, there are technology barriers inhibiting speech processing systems that work in extremely noisy conditions from meeting the demands of modern applications. This letter presents a new voice activity detector (VAD) for improving speech detection robustness in noisy environments and the performance of speech recognition systems. The algorithm defines an optimum likelihood ratio test (LRT) involving multiple and independent observations. The so-defined decision rule reports significant improvements in speech/nonspeech discrimination accuracy over existing VAD methods that are defined on a single observation and need empirically tuned hangover mechanisms. The algorithm has an inherent delay that, for several applications, including robust speech recognition, does not represent a serious implementation obstacle. An analysis of the overlap between the distributions of the decision variable shows the improved robustness of the proposed approach by means of a clear reduction of the classification error as the number of observations is increased. The proposed strategy is also compared to different VAD methods, including the G.729, AMR, and AFE standards, as well as recently reported algorithms showing a sustained advantage in speech/nonspeech detection accuracy and speech recognition performance.

Computer-aided diagnosis of Alzheimer's type dementia combining support vector machines and discriminant set of features

Alzheimers disease (AD) is the most common cause of dementia in the elderly and affects approximately 30 million individuals worldwide. With the growth of the older population in developed nations, the prevalence of AD is expected to triple over the next 50 years while its early diagnosis remains being a difficult task. Functional imaging modalities including Single Photon Emission Computed Tomography (SPECT) and positron emission tomography (PET) are often used with the aim of achieving early diagnosis. However, conventional evaluation of SPECT images often relies on manual reorientation, visual reading of tomographic slices and semiquantitative analysis of certain regions of interest (ROIs). These steps are time consuming, subjective and prone to error. This paper shows a fully automatic computer-aided diagnosis (CAD) system for improving the early detection of the AD. The proposed approach is based on image parameter selection and support vector machine (SVM) classification. A study is carried out in order to finding the ROIs and the most discriminant image parameters with the aim of reducing the dimensionality of the input space and improving the accuracy of the system. Among all the features evaluated, coronal standard deviation and sagittal correlation parameters are found to be the most effective ones for reducing the dimensionality of the input space and improving the diagnosis accuracy when a radial basis function (RBF) SVM is used. The proposed system yields a 90.38% accuracy in the early diagnosis of the AD and outperforms existing techniques including the voxel-as-features (VAF) approach.

Voice Activity Detection. Fundamentals and Speech Recognition System Robustness

An important drawback affecting most of the speech processing systems is the environmental noise and its harmful effect on the system performance. Examples of such systems are the new wireless communications voice services or digital hearing aid devices. In speech recognition, there are still technical barriers inhibiting such systems from meeting the demands of modern applications. Numerous noise reduction techniques have been developed to palliate the effect of the noise on the system performance and often require an estimate of the noise statistics obtained by means of a precise voice activity detector (VAD). Speech/non-speech detection is an unsolved problem in speech processing and affects numerous applications including robust speech recognition (Karray and Marting, 2003; Ramirez et al. 2003), discontinuous transmission (ITU, 1996; ETSI, 1999), real-time speech transmission on the Internet (Sangwan et al., 2002) or combined noise reduction and echo cancellation schemes in the context of telephony (Basbug et al., 2004; Gustafsson et al., 2002). The speech/non-speech classification task is not as trivial as it appears, and most of the VAD algorithms fail when the level of background noise increases. During the last decade, numerous researchers have developed different strategies for detecting speech on a noisy signal (Sohn et al., 1999; Cho and Kondoz, 2001; Gazor and Zhang, 2003, Armani et al., 2003) and have evaluated the influence of the VAD effectiveness on the performance of speech processing systems (Bouquin-Jeannes and Faucon, 1995). Most of the approaches have focussed on the development of robust algorithms with special attention being paid to the derivation and study of noise robust features and decision rules (Woo et al., 2000; Li et al., 2002; Marzinzik and Kollmeier, 2002). The different VAD methods include those based on energy thresholds (Woo et al., 2000), pitch detection (Chengalvarayan, 1999), spectrum analysis (Marzinzik and Kollmeier, 2002), zero-crossing rate (ITU, 1996), periodicity measure (Tucker, 1992), higher order statistics in the LPC residual domain (Nemer et al., 2001) or combinations of different features (ITU, 1993; ETSI, 1999; Tanyer and Ozer, 2000). This chapter shows a comprehensive approximation to the main challenges in voice activity detection, the different solutions that have been reported in a complete review of the state of the art and the evaluation frameworks that are normally used. The application of VADs for speech coding, speech enhancement and robust speech recognition systems is shown and discussed. Three different VAD methods are described and compared to standardized and

Principal component analysis-based techniques and supervised classification schemes for the early detection of Alzheimer's disease

In Alzheimers disease (AD) diagnosis process, functional brain image modalities such as Single-Photon Emission Computed Tomography (SPECT) and Positron Emission Tomography (PET) have been widely used to guide the clinicians. However, the current evaluation of these images entails a succession of manual reorientations and visual interpretation steps, which attach in some way subjectivity to the diagnostic. In this work, a complete computer aided diagnosis (CAD) system for an automatic evaluation of the neuroimages is presented. Principal component analysis (PCA)-based methods are proposed as feature extraction techniques, enhanced by other linear approaches such as linear discriminant analysis (LDA) or the measure of the Fisher discriminant ratio (FDR) for feature selection. The final features allow to face up the so-called small sample size problem and subsequently they are used for the study of neural networks (NN) and support vector machine (SVM) classifiers. The combination of the presented methods achieved accuracy results of up to 96.7% and 89.52% for SPECT and PET images, respectively, which means a significant improvement over the results obtained by the classical voxels-as-features (VAF) reference approach.

18F-FDG PET imaging analysis for computer aided Alzheimer's diagnosis

Finding sensitive and appropriate technologies for non-invasive observation and early detection of Alzheimers disease (AD) is of fundamental importance to develop early treatments. In this work we develop a fully automatic computer aided diagnosis (CAD) system for high-dimensional pattern classification of baseline ^1^8F-FDG PET scans from Alzheimers disease neuroimaging initiative (ADNI) participants. Image projection as feature space dimension reduction technique is combined with an eigenimage based decomposition for feature extraction, and support vector machine (SVM) is used to manage the classification task. A two folded objective is achieved by reaching relevant classification performance complemented with an image analysis support for final decision making. A 88.24% accuracy in identifying mild AD, with 88.64% specificity, and 87.70% sensitivity is obtained. This method also allows the identification of characteristic AD patterns in mild cognitive impairment (MCI) subjects.

SVM-based computer-aided diagnosis of the Alzheimer's disease using t-test NMSE feature selection with feature correlation weighting

This letter shows a computer-aided diagnosis (CAD) technique for the early detection of the Alzheimers disease (AD) based on single photon emission computed tomography (SPECT) image feature selection and a statistical learning theory classifier. The challenge of the curse of dimensionality is addressed by reducing the large dimensionality of the input data and defining normalized mean squared error features over regions of interest (ROI) that are selected by a t-test feature selection with feature correlation weighting. Thus, normalized mean square error (NMSE) features of cubic blocks located in the temporo-parietal brain region yields peak accuracy values of 98.3% for almost linear kernel support vector machine (SVM) defined over the 20 most discriminative features extracted. This new method outperformed recent developed methods for early AD diagnosis.

An effective subband OSF-based VAD with noise reduction for robust speech recognition

An effective voice activity detection (VAD) algorithm is proposed for improving speech recognition performance in noisy environments. The approach is based on the determination of the speech/nonspeech divergence by means of specialized order statistics filters (OSFs) working on the subband log-energies. This algorithm differs from many others in the way the decision rule is formulated. Instead of making the decision based on the current frame, it uses OSFs on the subband log-energies which significantly reduces the error probability when discriminating speech from nonspeech in a noisy signal. Clear improvements in speech/nonspeech discrimination accuracy demonstrate the effectiveness of the proposed VAD. It is shown that an increase of the OSF order leads to a better separation of the speech and noise distributions, thus allowing a more effective discrimination and a tradeoff between complexity and performance. The algorithm also incorporates a noise reduction block working in tandem with the VAD and showed to further improve its accuracy. A previous noise reduction block also improves the accuracy in detecting speech and nonspeech. The experimental analysis carried out on the AURORA databases and tasks provides an extensive performance evaluation together with an exhaustive comparison to the standard VADs such as ITU G.729, GSM AMR, and ETSI AFE for distributed speech recognition (DSR), and other recently reported VADs.

NMF-SVM Based CAD Tool Applied to Functional Brain Images for the Diagnosis of Alzheimer's Disease

This paper presents a novel computer-aided diagnosis (CAD) technique for the early diagnosis of the Alzheimers disease (AD) based on nonnegative matrix factorization (NMF) and support vector machines (SVM) with bounds of confidence. The CAD tool is designed for the study and classification of functional brain images. For this purpose, two different brain image databases are selected: a single photon emission computed tomography (SPECT) database and positron emission tomography (PET) images, both of them containing data for both Alzheimers disease (AD) patients and healthy controls as a reference. These databases are analyzed by applying the Fisher discriminant ratio (FDR) and nonnegative matrix factorization (NMF) for feature selection and extraction of the most relevant features. The resulting NMF-transformed sets of data, which contain a reduced number of features, are classified by means of a SVM-based classifier with bounds of confidence for decision. The proposed NMF-SVM method yields up to 91% classification accuracy with high sensitivity and specificity rates (upper than 90%). This NMF-SVM CAD tool becomes an accurate method for SPECT and PET AD image classification.

SVM-based CAD system for early detection of the Alzheimer's disease using kernel PCA and LDA

Single-photon emission tomography (SPECT) imaging has been widely used to guide clinicians in the early Alzheimers disease (AD) diagnosis challenge. However, AD detection still relies on subjective steps carried out by clinicians, which entail in some way subjectivity to the final diagnosis. In this work, kernel principal component analysis (PCA) and linear discriminant analysis (LDA) are applied on functional images as dimension reduction and feature extraction techniques, which are subsequently used to train a supervised support vector machine (SVM) classifier. The complete methodology provides a kernel-based computer-aided diagnosis (CAD) system capable to distinguish AD from normal subjects with 92.31% accuracy rate for a SPECT database consisting of 91 patients. The proposed methodology outperforms voxels-as-features (VAF) that was considered as baseline approach, which yields 80.22% for the same SPECT database.