Enhancing Multichannel Laser-Doppler Vibrometry Signals with Application to (Carotid-Femoral) Pulse Transit Time Estimation.

Pulse-wave velocity (PWV) can be used to quantify arterial stiffness, allowing for a diagnosis of this condition. Multi-beam laser-doppler vibrometry offers a cheap, non-invasive and user-friendly alternative to measuring PWV, and its feasibility has been previously demonstrated in the H2020 project CARDIS. The two handpieces of the prototype CARDIS device measure skin displacement above main arteries at two different sites, yielding an estimate of the pulse-transit time (PTT) and, consequently, PWV. The presence of multiple beams (channels) on each handpiece can be used to enhance the underlying signal, improving the quality of the signal for PTT estimation and further analysis. We propose two methods for multi-channel LDV data processing: beamforming and beamforming-driven ICA. Beamforming is done by an SNR-weighted linear combination of the time-aligned channels, where the SNR is blindly estimated from the signal statistics. ICA uses the beamformer to resolve its inherent permutation and scale ambiguities. Both methods yield a single enhanced signal at each handpiece, where spurious peaks in the individual channels as well as stochastic noise are well suppressed in the output. Using the enhanced signals yields individual PTT estimates with a low spread compared to the baseline approach. While the enhancement is introduced in the context of PTT estimation, the approaches can be used to enhance signals in other biomedical applications of multi-channel LDV as well.

Investigations on the Optimal Estimation of Speech Envelopes for the Two-Stage Speech Enhancement.

Using the source-filter model of speech production, clean speech signals can be decomposed into an excitation component and an envelope component that is related to the phoneme being uttered. Therefore, restoring the envelope of degraded speech during speech enhancement can improve the intelligibility and quality of output. As the number of phonemes in spoken speech is limited, they can be adequately represented by a correspondingly limited number of envelopes. This can be exploited to improve the estimation of speech envelopes from a degraded signal in a data-driven manner. The improved envelopes are then used in a second stage to refine the final speech estimate. Envelopes are typically derived from the linear prediction coefficients (LPCs) or from the cepstral coefficients (CCs). The improved envelope is obtained either by mapping the degraded envelope onto pre-trained codebooks (classification approach) or by directly estimating it from the degraded envelope (regression approach). In this work, we first investigate the optimal features for envelope representation and codebook generation by a series of oracle tests. We demonstrate that CCs provide better envelope representation compared to using the LPCs. Further, we demonstrate that a unified speech codebook is advantageous compared to the typical codebook that manually splits speech and silence as separate entries. Next, we investigate low-complexity neural network architectures to map degraded envelopes to the optimal codebook entry in practical systems. We confirm that simple recurrent neural networks yield good performance with a low complexity and number of parameters. We also demonstrate that with a careful choice of the feature and architecture, a regression approach can further improve the performance at a lower computational cost. However, as also seen from the oracle tests, the benefit of the two-stage framework is now chiefly limited by the statistical noise floor estimate, leading to only a limited improvement in extremely adverse conditions. This highlights the need for further research on joint estimation of speech and noise for optimum enhancement.

Acoustic speech features in social comparison: how stress impacts the way you sound.

The use of speech as a digital biomarker to detect stress levels is increasingly gaining attention. Yet, heterogeneous effects of stress on specific acoustic speech features have been observed, possibly due to previous studies' use of different stress labels/categories and the lack of solid stress induction paradigms or validation of experienced stress. Here, we deployed a controlled, within-subject psychosocial stress induction experiment in which participants received both neutral (control condition) and negative (negative condition) comparative feedback after solving a challenging cognitive task. This study is the first to use a (non-actor) within-participant design that verifies a successful stress induction using both self-report (i.e., decreased reported valence) and physiological measures (i.e., increased heart rate acceleration using event-related cardiac responses during feedback exposure). Analyses of acoustic speech features showed a significant increase in Fundamental Frequency (F0) and Harmonics-to-Noise Ratio (HNR), and a significant decrease in shimmer during the negative feedback condition. Our results using read-out-loud speech comply with earlier research, yet we are the first to validate these results in a well-controlled but ecologically-valid setting to guarantee the generalization of our findings to real-life settings. Further research should aim to replicate these results in a free speech setting to test the robustness of our findings for real-world settings and should include semantics to also take into account what you say and not only how you say it.

Portable and Non-Intrusive Fill-State Detection for Liquid-Freight Containers Based on Vibration Signals.

Remote, automated querying of fill-states of liquid-freight containers can significantly boost the operational efficiency of rail- and storage-yards. Most existing methods for fill-state detection are intrusive, or require sophisticated instrumentation and specific testing conditions, making them unsuitable here, due to the noisy and changeable surroundings and restricted access to the interior. We present a non-intrusive system that exploits the influence of the fill-state on the container's response to an external excitation. Using a solenoid and accelerometer mounted on the exterior wall of the container, to generate pulsed excitation and to measure the container response, the fill-state can be detected. The decision can be either a binary (empty/non-empty) label or a (quantised) prediction of the liquid level. We also investigate the choice of the signal features for the detection/classification, and the placement of the sensor and actuator. Experiments conducted in real settings validate the algorithms and the prototypes. Results show that the placement of the sensor and actuator along the base of the container is the best in terms of detection accuracy. In terms of signal features, linear predictive cepstral coefficients possess sufficient discriminative information. The prediction accuracy is 100% for binary classification and exceeds 80% for quantised level prediction.

Speech as an indicator for psychosocial stress: A network analytic approach.

Recently, the possibilities of detecting psychosocial stress from speech have been discussed. Yet, there are mixed effects and a current lack of clarity in relations and directions for parameters derived from stressed speech. The aim of the current study is - in a controlled psychosocial stress induction experiment - to apply network modeling to (1) look into the unique associations between specific speech parameters, comparing speech networks containing fundamental frequency (F0), jitter, mean voiced segment length, and Harmonics-to-Noise Ratio (HNR) pre- and post-stress induction, and (2) examine how changes pre- versus post-stress induction (i.e., change network) in each of the parameters are related to changes in self-reported negative affect. Results show that the network of speech parameters is similar after versus before the stress induction, with a central role of HNR, which shows that the complex interplay and unique associations between each of the used speech parameters is not impacted by psychosocial stress (aim 1). Moreover, we found a change network (consisting of pre-post stress difference values) with changes in jitter being positively related to changes in self-reported negative affect (aim 2). These findings illustrate - for the first time in a well-controlled but ecologically valid setting - the complex relations between different speech parameters in the context of psychosocial stress. Longitudinal and experimental studies are required to further investigate these relationships and to test whether the identified paths in the networks are indicative of causal relationships.

Template Matching and Matrix Profile for Signal Quality Assessment of Carotid and Femoral Laser Doppler Vibrometer Signals.

Background: Laser-Doppler Vibrometry (LDV) is a laser-based technique that allows measuring the motion of moving targets with high spatial and temporal resolution. To demonstrate its use for the measurement of carotid-femoral pulse wave velocity, a prototype system was employed in a clinical feasibility study. Data were acquired for analysis without prior quality control. Real-time application, however, will require a real-time assessment of signal quality. In this study, we (1) use template matching and matrix profile for assessing the quality of these previously acquired signals; (2) analyze the nature and achievable quality of acquired signals at the carotid and femoral measuring site; (3) explore models for automated classification of signal quality. Methods: Laser-Doppler Vibrometry data were acquired in 100 subjects (50M/50F) and consisted of 4-5 sequences of 20-s recordings of skin displacement, differentiated two times to yield acceleration. Each recording consisted of data from 12 laser beams, yielding 410 carotid-femoral and 407 carotid-carotid recordings. Data quality was visually assessed on a 1-5 scale, and a subset of best quality data was used to construct an acceleration template for both measuring sites. The time-varying cross-correlation of the acceleration signals with the template was computed. A quality metric constructed on several features of this template matching was derived. Next, the matrix-profile technique was applied to identify recurring features in the measured time series and derived a similar quality metric. The statistical distribution of the metrics, and their correlates with basic clinical data were assessed. Finally, logistic-regression-based classifiers were developed and their ability to automatically classify LDV-signal quality was assessed. Results: Automated quality metrics correlated well with visual scores. Signal quality was negatively correlated with BMI for femoral recordings but not for carotid recordings. Logistic regression models based on both methods yielded an accuracy of minimally 80% for our carotid and femoral recording data, reaching 87% for the femoral data. Conclusion: Both template matching and matrix profile were found suitable methods for automated grading of LDV signal quality and were able to generate a quality metric that was on par with the signal quality assessment of the expert. The classifiers, developed with both quality metrics, showed their potential for future real-time implementation.

A robust sequential hypothesis testing method for brake squeal localisation.

This contribution deals with the in situ detection and localisation of brake squeal in an automobile. As brake squeal is emitted from regions known a priori, i.e., near the wheels, the localisation is treated as a hypothesis testing problem. Distributed microphone arrays, situated under the automobile, are used to capture the directional properties of the sound field generated by a squealing brake. The spatial characteristics of the sampled sound field is then used to formulate the hypothesis tests. However, in contrast to standard hypothesis testing approaches of this kind, the propagation environment is complex and time-varying. Coupled with inaccuracies in the knowledge of the sensor and source positions as well as sensor gain mismatches, modelling the sound field is difficult and standard approaches fail in this case. A previously proposed approach implicitly tried to account for such incomplete system knowledge and was based on ad hoc likelihood formulations. The current paper builds upon this approach and proposes a second approach, based on more solid theoretical foundations, that can systematically account for the model uncertainties. Results from tests in a real setting show that the proposed approach is more consistent than the prior state-of-the-art. In both approaches, the tasks of detection and localisation are decoupled for complexity reasons. The localisation (hypothesis testing) is subject to a prior detection of brake squeal and identification of the squeal frequencies. The approaches used for the detection and identification of squeal frequencies are also presented. The paper, further, briefly addresses some practical issues related to array design and placement.

Ideal time-frequency masking algorithms lead to different speech intelligibility and quality in normal-hearing and cochlear implant listeners.

Hearing impaired listeners using cochlear implants (CIs) suffer from a decrease in speech intelligibility (SI) in adverse listening conditions. Time-frequency masks are often applied to perform noise suppression in an attempt to increase SI. Two important masks are the so-called ideal binary mask (IBM) with its binary weights and the ideal Wiener filter (IWF) with its continuous weights. It is unclear which of the masks has the highest potential for SI and speech quality enhancement in CI users. In this study, both approaches for SI and quality enhancement were compared. The investigations were conducted in normal-hearing (NH) subjects listening to noise vocoder CI simulations and in CI users. The potential for SI improvement was assessed in a sentence recognition task with ideal mask estimates in multitalker babble and with an interfering talker. The robustness of the approaches was evaluated with simulated estimation errors. CI users assessed the speech quality in a preference rating. The IWF outperformed the IBM in NH listeners. In contrast, no significant difference was obtained in CI users. Estimation errors degraded SI in CI users for both approaches. In terms of quality, the IWF outperformed, slightly, the IBM processed signals. The outcomes of this study suggest that the mask pattern is not that crucial for CIs. Results of speech enhancement algorithms obtained with NH subjects listening to vocoded or normally processed stimuli do not translate to CI users. This outcome means that the effect of new strategies has to be quantified with the user group considered.

A unified treatment of the reference estimation problem in depth EEG recordings.

The starting point of this paper is the analysis of the reference problem in intra-cerebral electroencephalographic (iEEG) recordings. It is well accepted that both surface and depth EEG signals are always recorded with respect to some unknown time-varying signal called reference. This article discusses different methods for determining and reducing the influence of the reference signal for the iEEG signals. In particular, we derive optimal approaches for the estimation of the reference signal in iEEG recording setups and demonstrate their relation to the well-known minimum power/variance distortionless response approaches derived for general array and antenna signal processing applications. We show that the proposed approaches achieve optimal performance in terms of estimation error and that they outperform other reference identification methods proposed in the literature. The developed algorithms are illustrated on simulated examples and on real iEEG signals.