Spatial suppression of peripheral regions (outer volume suppression) is used in MR spectroscopic imaging (MRSI) to reduce contamination from strong lipid and water signals. The manual placement of outer volume suppression slices requires significant operator interaction, which is time consuming and introduces variability in volume coverage. Placing a large number of outer volume saturation bands for volumetric MRSI studies is particularly challenging and time consuming, and becomes unmanageable as the number of suppression bands increase. In this study a method is presented that automatically segments a high-resolution MR image in order to identify the peripheral lipid containing regions. This method computes an optimized placement of suppression bands in three dimensions, and is based on the maximization of a criterion function. This criterion function maximizes coverage of peripheral lipid containing areas and minimizes suppression of cortical brain regions, and regions outside of the head.Computer simulation demonstrates automatic placement of sixtenn suppression slices to form a convex hull that covers peripheral lipid containing regions above the base of the brain. In vivo metabolite mapping obtained with short TE proton-echo-planar spectroscopic-imaging (PEPSI) shows that the automatic method yields a placement of suppression slices that is very similar to that of a skilled human operator in terms of lipid suppression and usable brain voxels.
The usage of decision support tools in emergency departments, based on predictive models, capable of estimating the probability of admission for patients in the emergency department may give nursing staff the possibility of allocating resources in advance. We present a methodology for developing and building one such system for a large specialized care hospital using a logistic regression and an artificial neural network model using nine routinely collected variables available right at the end of the triage process.A database of 255.668 triaged nonobstetric emergency department presentations from the Ramon y Cajal University Hospital of Madrid, from January 2011 to December 2012, was used to develop and test the models, with 66% of the data used for derivation and 34% for validation, with an ordered nonrandom partition. On the validation dataset areas under the receiver operating characteristic curve were 0.8568 (95% confidence interval, 0.8508-0.8583) for the logistic regression model and 0.8575 (95% confidence interval, 0.8540-0. 8610) for the artificial neural network model. χ Values for Hosmer-Lemeshow fixed "deciles of risk" were 65.32 for the logistic regression model and 17.28 for the artificial neural network model. A nomogram was generated upon the logistic regression model and an automated software decision support system with a Web interface was built based on the artificial neural network model.
This paper proposes a speech-based method for automatic depression classification. The system is based on ensemble learning for Convolutional Neural Networks (CNNs) and is evaluated using the data and the experimental protocol provided in the Depression Classification Sub-Challenge (DCC) at the 2016 Audio–Visual Emotion Challenge (AVEC-2016). In the pre-processing phase, speech files are represented as a sequence of log-spectrograms and randomly sampled to balance positive and negative samples. For the classification task itself, first, a more suitable architecture for this task, based on One-Dimensional Convolutional Neural Networks, is built. Secondly, several of these CNN-based models are trained with different initializations and then the corresponding individual predictions are fused by using an Ensemble Averaging algorithm and combined per speaker to get an appropriate final decision. The proposed ensemble system achieves satisfactory results on the DCC at the AVEC-2016 in comparison with a reference system based on Support Vector Machines and hand-crafted features, with a CNN+LSTM-based system called DepAudionet, and with the case of a single CNN-based classifier.
Hidden Markov Models (HMMs) are, undoubtedly, the most employed core technique for Automatic Speech Recognition (ASR). Nevertheless, we are still far from achieving high-performance ASR systems. Some alternative approaches, most of them based on Artificial Neural Networks (ANNs), were proposed during the late eighties and early nineties. Some of them tackled the ASR problem using predictive ANNs, while others proposed hybrid HMM/ANN systems. However, despite some achievements, nowadays, the preponderance of Markov Models is a fact.During the last decade, however, a new tool appeared in the field of machine learning that has proved to be able to cope with hard classification problems in several fields of application: the Support Vector Machines (SVMs). The SVMs are effective discriminative classifiers with several outstanding characteristics, namely: their solution is that with maximum margin; they are capable to deal with samples of a very higher dimensionality; and their convergence to the minimum of the associated cost function is guaranteed.These characteristics have made SVMs very popular and successful. In this chapter we discuss their strengths and weakness in the ASR context and make a review of the current state-of-the-art techniques. We organize the contributions in two parts: isolated-word recognition and continuous speech recognition. Within the first part we review several techniques to produce the fixed-dimension vectors needed for original SVMs. Afterwards we explore more sophisticated techniques based on the use of kernels capable to deal with sequences of different length. Among them is the DTAK kernel, simple and effective, which rescues an old technique of speech recognition: Dynamic Time Warping (DTW). Within the second part, we describe some recent approaches to tackle more complex tasks like connected digit recognition or continuous speech recognition using SVMs. Finally we draw some conclusions and outline several ongoing lines of research.
Abstract-The Internet Protocol (IP) environment poses two relevant sources of distortion to the speech recognition problem: lossy speech coding and packet loss. In this paper, we propose a new front-end for speech recognition over IP networks. Specifically, we suggest extracting the recognition feature vectors directly from the encoded speech (i.e., the bit stream) instead of decoding it and subsequently extracting the feature vectors. This approach offers two significant benefits. First, the recognition system is only affected by the quantization distortion of the spectral envelope. Thus, we are avoiding the influence of other sources of distortion due the encoding-decoding process. Second, when packet loss occurs, our front-end becomes more effective since it is not constrained to the error handling mechanism of the codec. We have considered the ITU G.723.1 standard codec, which is one of the most preponderant coding algorithms in voice over IP (VoIP) and compared the proposed front-end with the conventional approach in two automatic speech recognition (ASR) tasks, namely, speaker-independent isolated digit recognition and speaker-independent continuous speech recognition. In general, our approach outperforms the conventional procedure, for a variety of simulated packet loss rates. Furthermore, the improvement is higher as network conditions worsen.
In this paper, we propose a new front-end for Acoustic Event Classification tasks (AEC). First, we study the spectral characteristics of different acoustic events in comparison with the structure of speech spectra. Second, from the findings of this study, we propose a new parameterization for AEC, which is an extension of the conventional Mel Frequency Cepstrum Coefficients (MFCC) and is based on the high pass filtering of the acoustic event signal. The proposed front-end have been tested in clean and noisy conditions and compared to the conventional MFCC in an AEC task. Results support the fact that the high pass filtering of the audio signal is, in general terms, beneficial for the system, showing that the removal of frequencies below 100-275 Hz in the feature extraction process in clean conditions and below 400-500 Hz in noisy conditions, improves significantly the performance of the system with respect to the baseline.
A Speaker Identification system for a personalized wearable device to combat gender-based violence is presented in this paper. Speaker recognition systems exhibit a decrease in performance when the user is under emotional or stress conditions, thus the objective of this paper is to measure the effects of stress in speech to ultimately try to mitigate their consequences on a speaker identification task, by using data augmentation techniques specifically tailored for this purpose given the lack of data resources for this condition. An extensive experimentation has been carried out for assessing the effectiveness of the proposed techniques. First, we conclude that the best performance is always obtained when naturally stressed samples are included in the training set, and second, when these are not available, their substitution and augmentation with synthetically generated stress-like samples improves the performance of the system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.