Search

Sound event detection systems are widely used in various applications such as surveillance and environmental monitoring where data is automatically collected, processed, and sent to a cloud for sound recognition. However, this process may inadvertently reveal sensitive information about users or their surroundings, hence raising privacy concerns. In this study, we propose a novel adversarial training method for learning representations of audio recordings that effectively prevents the detection of speech activity from the latent features of the recordings. The proposed method trains a model to generate invariant latent representations of speech-containing audio recordings that cannot be distinguished from non-speech recordings by a speech classifier. The novelty of our work is in the optimization algorithm, where the speech classifier's weights are regularly replaced with the weights of classifiers trained in a supervised manner. This increases the discrimination power of the speech classifier constantly during the adversarial training, motivating the model to generate latent representations in which speech is not distinguishable, even using new speech classifiers trained outside the adversarial training loop. The proposed method is evaluated against a baseline approach with no privacy measures and a prior adversarial training method, demonstrating a significant reduction in privacy violations compared to the baseline approach. Additionally, we show that the prior adversarial method is practically ineffective for this purpose.

A major part of important mammalian respiratory allergens belongs to the lipocalin family of proteins. By this time, 19 respiratory mammalian lipocalin allergens have been registered in the WHO/IUIS Allergen Nomenclature Database. Originally, lipocalins, small extracellular proteins (molecular mass ca. 20 kDa), were characterized as transport proteins but they are currently known to exert a variety of biological functions. The three-dimensional structure of lipocalins is well-preserved, and lipocalin allergens can exhibit high amino acid identities, in several cases more than 50%. Lipocalins contain an internal ligand-binding site where they can harbor small principally hydrophobic molecules. Another characteristic feature is their capacity to bind to specific cell-surface receptors. In all, the physicochemical properties of lipocalin allergens do not offer any straightforward explanations for their allergenicity. Allergic sensitization begins at epithelial barriers where diverse insults through pattern recognition receptors awaken innate immunity. This front-line response is manifested by epithelial barrier-associated cytokines which together with other components of immunity can initiate the sensitization process. In the following, the crucial factor in allergic sensitization is interleukin (IL)-4 which is needed for stabilizing and promoting the type 2 immune response. The source for IL-4 has been searched widely. Candidates for it may be non-professional antigen-presenting cells, such as basophils or mast cells, as well as CD4+ T cells. The synthesis of IL-4 by CD4+ T cells requires T cell receptor engagement, i.e., the recognition of allergen peptides, which also provides the specificity for sensitization. Lipocalin and innate immunity-associated cell-surface receptors are implicated in facilitating the access of lipocalin allergens into the immune system. However, the significance of this for allergic sensitization is unclear, as the recognition by these receptors has been found to produce conflicting results. As to potential adjuvants associated with mammalian lipocalin allergens, the hydrophobic ligands transported by lipocalins have not been reported to enhance sensitization while it is justified to suppose that lipopolysaccharide plays a role in it. Taken together, type 2 immunity to lipocalin allergens appears to be a harmful immune response resulting from a combination of signals involving both the innate and adaptive immunities.

It has been suggested that early cry parameters are connected to later cognitive abilities. The present study is the first to investigate whether the acoustic features of infant cry are associated with cognitive development already during the first year, as measured by oculomotor orienting and attention disengagement. Cry sounds for acoustic analyses (fundamental frequency; F0) were recorded in two neonatal cohorts at the age of 0–8 days (Tampere, Finland) or at 6 weeks (Cape Town, South Africa). Eye tracking was used to measure oculomotor orienting to peripheral visual stimuli and attention disengagement from central stimuli at 8 months (Tampere) or at 6 months (Cape Town) of age. Only a marginal positive correlation between fundamental frequency of cry (F0) and visual attention disengagement was observed in the Tampere cohort, but not in the Cape Town cohort. This correlation indicated that infants from the Tampere cohort with a higher neonatal F0 were marginally slower to shift their gaze away from the central stimulus to the peripheral stimulus. No associations between F0 and oculomotor orienting were observed in either cohort. We discuss possible factors influencing the current pattern of results suggesting a lack of replicable associations between neonatal cry and visual attention and suggest directions for future research investigating the potential of early cry analysis in predicting later cognitive development.

Abstract This paper considers a scenario when we have multiple pre-trained detectors for detecting an event and a small dataset for training a combined detection system. We build the combined detector as a Boolean function of thresholded detector scores and implement it as a binary classification cascade. The cascade structure is computationally efficient by providing the possibility to early termination. For the proposed Boolean combination function, the computational load of classification is reduced whenever the function becomes determinate before all the component detectors have been utilized. We also propose an algorithm, which selects all the needed thresholds for the component detectors within the proposed Boolean combination. We present results on two audio-visual datasets, which prove the efficiency of the proposed combination framework. We achieve state-of-the-art accuracy with substantially reduced computation time in laughter detection task, and our algorithm finds better thresholds for the component detectors within the Boolean combination than the other algorithms found in the literature.

Allergic diseases compose a serious challenge for modern societies. Their individual, medical and economical burden is large. As humans spend most of their time indoors, exposure to indoor allergens is a significant contributor to the development of allergic sensitization and respiratory allergies, such as allergic rhinoconjunctivitis and asthma. One important source of indoor allergens are pets, in particular cats and dogs. Allergens from these and other mammals spread effectively and they are encountered widely in public places. If patient education, allergen avoidance and pharmacotherapy do not suffice for controlling the symptoms of pet allergy, allergen immunotherapy can be a treatment option. Current information on allergen immunotherapy in pet allergy suggests that it can be effective in reducing allergic symptoms. However, the low number of high-quality randomized controlled trials of allergen immunotherapy in pet allergy warrants for further investigations.

Abstract Automatic extraction of acoustic regions of interest from recordings captured in realistic clinical environments is a necessary preprocessing step in any cry analysis system. In this study, we propose a hidden Markov model (HMM) based audio segmentation method to identify the relevant acoustic parts of the cry signal (i.e., expiratory and inspiratory phases) from recordings made in natural environments with various interfering acoustic sources. We examine and optimize the performance of the system by using different audio features and HMM topologies. In particular, we propose using fundamental frequency and aperiodicity features. We also propose a method for adapting the segmentation system trained on acoustic material captured in a particular acoustic environment to a different acoustic environment by using feature normalization and semi-supervised learning (SSL). The performance of the system was evaluated by analyzing a total of 3 h and 10 min of audio material from 109 infants, captured in a variety of recording conditions in hospital wards and clinics. The proposed system yields frame-based accuracy up to 89.2%. We conclude that the proposed system offers a solution for automated segmentation of cry signals in cry analysis applications.

Long-range correlated temporal fluctuations in the beats of musical rhythms are an inevitable consequence of human action. According to recent studies, such fluctuations also lead to a favored listening experience. The scaling laws of amplitude variations in rhythms, however, are widely unknown. Here we use highly sensitive onset detection and time series analysis to study the amplitude and temporal fluctuations of Jeff Porcaro's one-handed hi-hat pattern in "I Keep Forgettin'"-one of the most renowned 16th note patterns in modern drumming. We show that fluctuations of hi-hat amplitudes and interbeat intervals (times between hits) have clear long-range correlations and short-range anticorrelations separated by a characteristic time scale. In addition, we detect subtle features in Porcaro's drumming such as small drifts in the 16th note pulse and non-trivial periodic two-bar patterns in both hi-hat amplitudes and intervals. Through this investigation we introduce a step towards statistical studies of the 20th and 21st century music recordings in the framework of complex systems. Our analysis has direct applications to the development of drum machines and to drumming pedagogy.

This paper presents and discusses various metrics proposed for evaluation of polyphonic sound event detection systems used in realistic situations where there are typically multiple sound sources active simultaneously. The system output in this case contains overlapping events, marked as multiple sounds detected as being active at the same time. The polyphonic system output requires a suitable procedure for evaluation against a reference. Metrics from neighboring fields such as speech recognition and speaker diarization can be used, but they need to be partially redefined to deal with the overlapping events. We present a review of the most common metrics in the field and the way they are adapted and interpreted in the polyphonic case. We discuss segment-based and event-based definitions of each metric and explain the consequences of instance-based and class-based averaging using a case study. In parallel, we provide a toolbox containing implementations of presented metrics.

The paper considers the task of recognizing phonemes and words from a singing input by using a phonetic hidden Markov model recognizer. The system is targeted to both monophonic singing and singing in polyphonic music. A vocal separation algorithm is applied to separate the singing from polyphonic music. Due to the lack of annotated singing databases, the recognizer is trained using speech and linearly adapted to singing. Global adaptation to singing is found to improve singing recognition performance. Further improvement is obtained by gender-specific adaptation. We also study adaptation with multiple base classes defined by either phonetic or acoustic similarity. We test phoneme-level and word-level n-gram language models. The phoneme language models are trained on the speech database text. The large-vocabulary word-level language model is trained on a database of textual lyrics. Two applications are presented. The recognizer is used to align textual lyrics to vocals in polyphonic music, obtaining an average error of 0.94 seconds for line-level alignment. A query-by-singing retrieval application based on the recognized words is also constructed; in 57% of the cases, the first retrieved song is the correct one.

This paper proposes a query by example system for generic audio. We estimate the similarity of the example signal and the samples in the queried database by calculating the distance between the probability density functions (pdfs) of their frame-wise acoustic features. Since the features are continuous valued, we propose to model them using Gaussian mixture models (GMMs) or hidden Markov models (HMMs). The models parametrize each sample efficiently and retain sufficient information for similarity measurement. To measure the distance between the models, we apply a novel Euclidean distance, approximations of Kullback-Leibler divergence, and a cross-likelihood ratio test. The performance of the measures was tested in simulations where audio samples are automatically retrieved from a general audio database, based on the estimated similarity to a user-provided example. The simulations show that the distance between probability density functions is an accurate measure for similarity. Measures based on GMMs or HMMs are shown to produce better results than that of the existing methods based on simpler statistics or histograms of the features. A good performance with low computational cost is obtained with the proposed Euclidean distance.