Emotion Recognition Robust to Indoor Environmental Distortions and Non-targeted Emotions Using Out-of-distribution Detection

The rapid development of machine learning on acoustic signal processing has resulted in many solutions for detecting emotions from speech. Early works were developed for clean and acted speech and for a fixed set of emotions. Importantly, the datasets and solutions assumed that a person only exhibited one of these emotions. More recent work has continually been adding realism to emotion detection by considering issues such as reverberation, de-amplification, and background noise, but often considering one dataset at a time, and also assuming all emotions are accounted for in the model. We significantly improve realistic considerations for emotion detection by (i) more comprehensively assessing different situations by combining the five common publicly available datasets as one and enhancing the new dataset with data augmentation that considers reverberation and de-amplification, (ii) incorporating 11 typical home noises into the acoustics, and (iii) considering that in real situations a person may be exhibiting many emotions that are not currently of interest and they should not have to fit into a pre-fixed category nor be improperly labeled. Our novel solution combines CNN with out-of-data distribution detection. Our solution increases the situations where emotions can be effectively detected and outperforms a state-of-the-art baseline.

A Retrospective Study of the Effects of Traumatic Brain Injury on Auditory Function: From a Clinical Perspective

Purpose: The main purpose of this retrospective study was to identify auditory dysfunctions related to traumatic brain injury (TBI) in individuals evaluated in an Audiology clinic. Method: Peripheral and central auditory evaluations were performed from March 2014 to June 2018 in 26 patients (14 males) with TBI. The age of the participants ranged from 9 to 59 years old (34.24 ± 15.21). Six participants had blast-related TBI and 20 had blunt force TBI. Sixteen experienced a single TBI event whereas ten experienced several. Correlation analyses were performed to verify the relationship, if any, between the number of auditory tests failed and the number, type, and severity of TBIs. Result: All participants failed at least one auditory test. Nearly 60% had abnormal results on degraded speech tests (compressed and echoed, filtered or in background noise) and 25% had a high frequency hearing loss. There was no statistically significant correlation between the number of auditory tests failed and the number, type, and severity of TBIs. Conclusion: Results indicated negative and heterogenous effects of TBI on peripheral and central auditory function and highlighted the need for a more extensive auditory assessment in individuals with TBI.

Manifold Alignment Aware Ants: A Markovian Process for Manifold Extraction

The presence of manifolds is a common assumption in many applications, including astronomy and computer vision. For instance, in astronomy, low-dimensional stellar structures, such as streams, shells, and globular clusters, can be found in the neighborhood of big galaxies such as the Milky Way. Since these structures are often buried in very large data sets, an algorithm, which can not only recover the manifold but also remove the background noise (or outliers), is highly desirable. While other works try to recover manifolds either by pushing all points toward manifolds or by downsampling from dense regions, aiming to solve one of the problems, they generally fail to suppress the noise on manifolds and remove background noise simultaneously. Inspired by the collective behavior of biological ants in food-seeking process, we propose a new algorithm that employs several random walkers equipped with a local alignment measure to detect and denoise manifolds. During the walking process, the agents release pheromone on data points, which reinforces future movements. Over time the pheromone concentrates on the manifolds, while it fades in the background noise due to an evaporation procedure. We use the Markov chain (MC) framework to provide a theoretical analysis of the convergence of the algorithm and its performance. Moreover, an empirical analysis, based on synthetic and real-world data sets, is provided to demonstrate its applicability in different areas, such as improving the performance of t-distributed stochastic neighbor embedding (t-SNE) and spectral clustering using the underlying MC formulas, recovering astronomical low-dimensional structures, and improving the performance of the fast Parzen window density estimator.

THE EFFECT OF DIFFERENT OCCUPATIONAL BACKGROUND NOISES ON VOICE RECOGNITION ACCURACY

Voice recognition has become an integral part of our lives, commonly used in call centers and as part of virtual assistants. However, voice recognition is increasingly applied to more industrial uses. Each of these use cases has unique characteristics that may impact the effectiveness of voice recognition, which could impact industrial productivity, performance, or even safety. One of the most prominent among them is the unique background noises that are dominant in each industry. The existence of different machinery and different work layouts are primary contributors to this. Another important characteristic is the type of communication that is present in these settings. Daily communication often involves longer sentences uttered under relatively silent conditions, whereas communication in industrial settings is often short and conducted in loud conditions. In this study, we demonstrated the importance of taking these two elements into account by comparing the performances of two voice recognition algorithms under several background noise conditions: a regular Convolutional Neural Network (CNN) based voice recognition algorithm to an Auto Speech Recognition (ASR) based model with a denoising module. Our results indicate that there is a significant performance drop between the typical background noise use (white noise) and the rest of the background noises. Also, our custom ASR model with the denoising module outperformed the CNN based model with an overall performance increase between 14-35% across all background noises. . Both results give proof that specialized voice recognition algorithms need to be developed for these environments to reliably deploy them as control mechanisms.

Evaluation of contrast enhancement ultrasound images of Sonazoid microbubbles in tissue-mimicking phantom obtained by optimal Golay pulse compression

In contrast enhancement ultrasound (CEUS), the vasculature image can be formed from nonlinear echoes arising from microbubbles in a blood flow. The use of binary-coded pulse compression is promising for improving the contrast of CEUS images by suppressing background noise. However, the amplitudes of nonlinear echoes can be reduced, and sidelobes by nonlinear echoes can occur depending on the binary code. Optimal Golay codes with slight nonlinear-echo reduction and nonlinear sidelobe have been proposed. In this study, CEUS images obtained by optimal Golay pulse compression are evaluated through experiments using Sonazoid microbubbles flowing in a tissue-mimicking phantom.

Marimo actuated rover systems

Background The potential to directly harness photosynthesis to make actuators, biosensors and bioprocessors has been previously demonstrated in the literature. Herein, this capability has been expanded to more advanced systems — Marimo Actuated Rover Systems (MARS) — which are capable of autonomous, solar powered, movement. Results We demonstrate this ability is both a practical and viable alternative to conventional mobile platforms for exploration and dynamic environmental monitoring. Prototypes have been successfully tested to measure their speed of travel and ability to automatically bypass obstacles. Further, MARS is electromagnetically silent, thus avoiding the background noise generated by conventional electro/mechanical platforms which reduces instrument sensitivity. The cost of MARS is significantly lower than platforms based on conventional technology. Conclusions An autonomous, low-cost, lightweight, compact size, photosynthetically powered rover is reported. The potential for further system enhancements are identified and under development.

Time-Domain Joint Training Strategies of Speech Enhancement and Intent Classification Neural Models

Robustness against background noise and reverberation is essential for many real-world speech-based applications. One way to achieve this robustness is to employ a speech enhancement front-end that, independently of the back-end, removes the environmental perturbations from the target speech signal. However, although the enhancement front-end typically increases the speech quality from an intelligibility perspective, it tends to introduce distortions which deteriorate the performance of subsequent processing modules. In this paper, we investigate strategies for jointly training neural models for both speech enhancement and the back-end, which optimize a combined loss function. In this way, the enhancement front-end is guided by the back-end to provide more effective enhancement. Differently from typical state-of-the-art approaches employing on spectral features or neural embeddings, we operate in the time domain, processing raw waveforms in both components. As application scenario we consider intent classification in noisy environments. In particular, the front-end speech enhancement module is based on Wave-U-Net while the intent classifier is implemented as a temporal convolutional network. Exhaustive experiments are reported on versions of the Fluent Speech Commands corpus contaminated with noises from the Microsoft Scalable Noisy Speech Dataset, shedding light and providing insight about the most promising training approaches.

Parent-offspring and inter-offspring responses to conspecific vs heterospecific distress calls in two sympatric birds

Distress calls, as a type of alarm call, play important roles in expressing bodily condition and conveying information concerning predation threats. In this study, we examined the communication via distress calls in parent–offspring and inter-offspring interactions. First, we used playback of chick distress calls of two sympatric breeders, the vinous-throated parrotbill Sinosuthora webbiana and the oriental reed warbler Acrocephalus orientalis, to the adults/chicks of these two species respectively and measured the responses of conspecifics or heterospecifics. The playback-to-chicks experiment showed that both species of chicks reduced the number of begging calls and begging duration time as a response to conspecific/heterospecific distress calls compared with natural begging and background noise controls. However, reed warbler chicks also reduced beak opening frequency in the response to conspecific distress calls compared with other playback stimuli. Second, the results of the playback-to-adults experiment showed that reed warbler adults could eavesdrop on distress calls of conspecific neighbors and sympatric heterospecifics. Furthermore, the nest-leaving behavior of reed warblers did not differ significantly when they heard the distress calls of conspecifics or parrotbills. Finally, reed warbler adults responded to conspecific distress calls more quickly than to heterospecific distress calls, while parrotbill adults presented the opposite response. Our results supported the warn-kin hypothesis and show that chick distress calls play an important role in conveying risk and the condition of chicks to enhance individual fitness. In addition, we also found that eavesdropping on distress calls is a congenital behavior that begins in the chick stage.

Evaluation of Frequencies for the IoT Telemetry in Smart Agriculture

The IoT is becoming a widely known technology for the gathering of telemetry data, while mostly the concept of Smart cities is usually seen as the most challenging area for implementation. The different situations can be found in the smart agriculture concept, where different requirements and especially conditions exist. The purpose of this paper is to make an overview of IoT frequency bands available, with special focus on the situation in the EU, their theoretical usability and, using experimental measurements of typical background noise in different bands and calculations of transmission reliability on expected distance, estimate the practical usability of those technologies in the smart agriculture, compared to the smart city’s requirements. Most of the IoT installations outside 5G systems are in the 900 MHz band, but is this well-suitable for smart agriculture?