Background Auscultation is one of the first examinations that a patient is subjected to in a GP’s office, especially in relation to diseases of the respiratory system. However it is a highly subjective process and depends on the physician’s ability to interpret the sounds as determined by his/her psychoacoustical characteristics. Here, we present a cross-sectional assessment of the skills of physicians of different specializations and medical students in the classification of respiratory sounds in children. Methods and findings 185 participants representing different medical specializations took part in the experiment. The experiment comprised 24 respiratory system auscultation sounds. The participants were tasked with listening to, and matching the sounds with provided descriptions of specific sound classes. The results revealed difficulties in both the recognition and description of respiratory sounds. The pulmonologist group was found to perform significantly better than other groups in terms of number of correct answers. We also found that performance significantly improved when similar sound classes were grouped together into wider, more general classes. Conclusions These results confirm that ambiguous identification and interpretation of sounds in auscultation is a generic issue which should not be neglected as it can potentially lead to inaccurate diagnosis and mistreatment. Our results lend further support to the already widespread acknowledgment of the need to standardize the nomenclature of auscultation sounds (according to European Respiratory Society, International Lung Sounds Association and American Thoracic Society). In particular, our findings point towards important educational challenges in both theory (nomenclature) and practice (training).

In this article a DNN-based system for detection of three common voice disorders (vocal nodules, polyps and cysts; laryngeal neoplasm; unilateral vocal paralysis) is presented. The input to the algorithm is (at least 3-second long) audio recording of sustained vowel sound /a:/. The algorithm was developed as part of the "2018 FEMH Voice Data Challenge" organized by Far Eastern Memorial Hospital and obtained score value (defined in the challenge specification) of 77.44. This was the second best result before final submission. Final challenge results are not yet known during writing of this document. The document also reports changes that were made for the final submission which improved the score value in cross-validation by 0.6% points.

Annoyance ratings for artificially created noises, resembling the main characteristics of temporal wind turbine noise, were studied by means of a listening experiment involving 21 participants with normal hearing. Three types of stimuli were examined: broadband noise (−4 dB/octave), noise generated by moving cars, and narrowband noise. All stimuli had the sound level fluctuations typical for wind turbine noise. The magnitude of the sound level fluctuations was measured in a quantitative way, by using the characteristics of amplitude modulated sound: modulation rate and modulation depth. Our aim was to examine how the modulation rate and the modulation depth influence the noise annoyance assessment of broadband and narrowband amplitude modulated noises. Three different modulation rates, 1, 2 and 4 Hz, and sound level fluctuations (a measure of the modulation depth), 3, 6, 9 dB, were applied to each type of stimuli (with exception of noise generated by the moving cars) and investigated. The participants in the listening experiment were presented with sound stimuli in laboratory conditions and asked to rate their annoyance on a numerical scale. The results have shown a significant difference between the investigated conditions. The effect was particularly strong between the annoyance judgments of different types of noise (narrow and broadband), and modulated versus unmodulated noises. Temporal fluctuations occurring in wind turbine noise are very pertinent to the perception of annoyance and could be responsible for its being a relatively annoying noise source. The obtained results were discussed and compared to the typical modulation rates and level changes that occur in recordings of real wind turbine noise.

No abstract