Showing papers by "Yaniv Zigel published in 2011"

Supervector Dimension Reduction for Efficient Speaker Age Estimation Based on the Acoustic Speech Signal

Abstract: This paper presents a novel dimension reduction method which aims to improve the accuracy and the efficiency of speaker's age estimation systems based on speech signal. Two different age estimation approaches were studied and implemented; the first, age-group classification, and the second, precise age estimation using regression. These two approaches use the Gaussian mixture model (GMM) supervectors as features for a support vector machine (SVM) model. When a radial basis function (RBF) kernel is used, the accuracy is improved compared to using a linear kernel; however, the computation complexity is more sensitive to the feature dimension. Classic dimension reduction methods like principal component analysis (PCA) and linear discriminant analysis (LDA) tend to eliminate the relevant feature information and cannot always be applied without damaging the model's accuracy. In our study, a novel dimension reduction method was developed, the weighted-pairwise principal components analysis (WPPCA) based on the nuisance attribute projection (NAP) technique. This method projects the supervectors to a reduced space where the redundant within-class pairwise variability is eliminated. This method was applied and compared to the baseline system where no dimensionality reduction is done on the supervectors. The conducted experiments showed a dramatic speed-up in the SVM training testing time using reduced feature vectors. The system accuracy was improved by 5% for the classification system and by 10% for the regression system using the proposed dimension reduction method.

Automatic Detection of Obstructive Sleep Apnea Using Speech Signals

Abstract: Obstructive sleep apnea (OSA) is a common disorder associated with anatomical abnormalities of the upper airways that affects 5% of the population. Acoustic parameters may be influenced by the vocal tract structure and soft tissue properties. We hypothesize that speech signal properties of OSA patients will be different than those of control subjects not having OSA. Using speech signal processing techniques, we explored acoustic speech features of 93 subjects who were recorded using a text-dependent speech protocol and a digital audio recorder immediately prior to polysomnography study. Following analysis of the study, subjects were divided into OSA ( n = 67) and non-OSA (n = 26) groups. A Gaussian mixture model-based system was developed to model and classify between the groups; discriminative features such as vocal tract length and linear prediction coefficients were selected using feature selection technique. Specificity and sensitivity of 83% and 79% were achieved for the male OSA and 86% and 84% for the female OSA patients, respectively. We conclude that acoustic features from speech signals during wakefulness can detect OSA patients with good specificity and sensitivity. Such a system can be used as a basis for future development of a tool for OSA screening.

Adenotonsillectomy improves slow-wave activity in children with obstructive sleep apnoea.

Abstract: The aim of the present study was to estimate slow-wave activity (SWA), a marker of sleep homeostasis, in children with obstructive sleep apnoea (OSA) before and after adenotonsillectomy (AT) compared with untreated OSA children (comparison group). 14 children with OSA (mean ± sd age 6.4 ± 2.5 yrs; apnoea-hypopnoea index (AHI) 10.0 ± 10.3 events·h⁻¹) who underwent AT were consecutively recruited to the study. The comparison group comprised six retrospectively recruited children (age 5.4 ± 2.2 yrs; AHI 9.4 ± 7.6 events·h⁻¹) with OSA that did not undergo treatment. Electroencephalogram (derivation C3/A2) was analysed using spectral and waveform analysis to determine SWA energy and slow-wave slope. The same procedure was repeated 5.4 and 19 months later for the AT and comparison groups, respectively. AT improved respiration without a change in duration of sleep stages. Following AT, >50% elevation of SWA during the first two sleep cycles (p 30% following AT (p<0.03). No significant changes were found in SWA in the comparison group. Sleep homeostasis is considerably impaired in pre-pubescent children with OSA. AT restores more physiological sleep homeostasis in children with OSA. SWA analysis may provide a useful addition to standard sleep-stage analyses in children with OSA.

Apparatus and method for diagnosing obstructive sleep apnea

Abstract: An embodiment of the invention provides a method of diagnosing obstructive sleep apnea, the method comprising: acquiring a sleep sound signal comprising sounds made by a person during sleep; detecting a plurality of snore sounds in the sleep sound signal; determining a set of mel-frequency cepstral coefficients for each of the snore sounds; determining a characterizing feature for the sleep sound signal responsive to a sum of the variances of the cepstral coefficients; and using the characterizing feature to diagnose obstructive sleep apnea in the person.

Detection of obstructive sleep apnea using speech signal analysis.

Abstract: Obstructive sleep apnea (OSA) is a sleep disorder associated with several anatomical abnormalities of the upper airway. Our hypothesis is that it is possible to distinguish between OSA and non-OSA subjects by analyzing particular speech signal properties using an automatic computerized system. The database for this research was constructed from 90 male subjects who were recorded reading a one-minute speech protocol immediately prior to a full polysomnography study; specific phonemes were isolated using closed group phoneme identification; seven independent Gaussian mixture models (GMM)-based classifiers were implemented for the task of OSA \ non-OSA classification; a fusion process was designed to combine the scores of these classifiers and a validation procedure took place in order to examine the system’s performance. Results of 91.66% specificity and 91.66% sensitivity were achieved using a leave one out procedure when the data was manually segmented. The system performances were somewhat decreased when the automatic segmentation was used, resulting in 83.33% specificity and 81.25% sensitivity.

A Surface ECG-Based Algorithm to Determine the Atrial Refractoriness of Rodents During Electrophysiological Study

Abstract: Data regarding the atrial electrophysiology of rodents is hard to obtain. We hypothesized that the latency to the first R following programmed S1–S2 stimulation of the atria (defined as RRS2) is affected by atrial capture and may be utilized to determine the atrial refractoriness of rodents using a simple electrocardiogram (ECG)-based algorithm. ECG signals during programmed-stimulation protocols were evaluated in 24 anesthetized rats and 12 mice using an automated QRS detection program. In each S1–S2 stimulation the atrial capture was determined in the invasive recording and the RRS2 was determined independently in the ECG recording. Based on our hypothesis an algorithm was designed to determine atrial capture noninvasively and 95% confidence interval (95% CI) was calculated for the obtained specificity and sensitivity. In rats the ratio between RRS2 and the spontaneous RR interval (RRspon) could identify two decision-relevant ranges: RRS2/RRspon 1.113; both indicated capture of S2. In contrast, RRS2/RRspon between these values indicated failure of atrial capture. This algorithm reached sensitivity of 97.7% (95% CI 96.0–99.4%) and specificity of 96.8% (95% CI 94.8–98.8%). Following rapid atrial pacing the same algorithm reached sensitivity of 94.96% (95% CI 92.0–97.9%) and specificity of 99% (95% CI 97.7–100%). In mice, difficulties in QRS detection were encountered which somewhat limited the ECG analysis. Our results indicate that atrial electrical capture affects the latency to the first R following S1–S2 stimulation in a predictable manner. This finding may advance the ability to detect the atrial refractoriness of rodents using a simple, minimally invasive, experimental setting.