Ambient Assisted Living (AAL) has become a powerful alternative to improving the life quality of elderly and partially dependent people in their own living environments. In this regard, tele-care and remote surveillance AAL applications have emerged as a hot research topic in this domain. These services aim to infer the patients’ status by means of centralized architectures that collect data from a set of sensors deployed in their living environment. However, when the size of the scenario and number of patients to be monitored increase (e.g., residential areas, retirement homes), these systems typically struggle at processing all associated data and providing a reasonable output in real time. The purpose of this paper is to present a fog-inspired distributed architecture to collect, analyze and identify up to nine acoustic events that represent abnormal behavior or dangerous health conditions in large-scale scenarios. Specifically, the proposed platform collects data from a set of wireless acoustic sensors and runs an automatic two-stage audio event classification process to decide whether or not to trigger an alarm. Conducted experiments over a labeled dataset of 7116 s based on the priorities of the Fundació Ave Maria health experts have obtained an overall accuracy of 94.6%.

Continuous exposure to urban noise has been found to be one of the major threats to citizens’ health. In this regard, several organizations are devoting huge efforts to designing new in-field systems to identify the acoustic sources of these threats to protect those citizens at risk. Typically, these prototype systems are composed of expensive components that limit their large-scale deployment and thus reduce the scope of their measurements. This paper aims to present a highly scalable low-cost distributed infrastructure that features a ubiquitous acoustic sensor network to monitor urban sounds. It takes advantage of (1) low-cost microphones deployed in a redundant topology to improve their individual performance when identifying the sound source, (2) a deep-learning algorithm for sound recognition, (3) a distributed data-processing middleware to reach consensus on the sound identification, and (4) a custom planar antenna with an almost isotropic radiation pattern for the proper node communication. This enables practitioners to acoustically populate urban spaces and provide a reliable view of noises occurring in real time. The city of Barcelona (Spain) and the UrbanSound8K dataset have been selected to analytically validate the proposed approach. Results obtained in laboratory tests endorse the feasibility of this proposal.

Many people living in urban environments nowadays are overexposed to noise, which results in adverse effects on their health. Thus, urban sound monitoring has emerged as a powerful tool that might enable public administrations to automatically identify and quantify noise pollution. Therefore, identifying multiple and simultaneous acoustic sources in these environments in a reliable and cost-effective way has emerged as a hot research topic. The purpose of this paper is to propose a two-stage classifier able to identify, in real time, a set of up to 21 urban acoustic events that may occur simultaneously (i.e., multilabel), taking advantage of physical redundancy in acoustic sensors from a wireless acoustic sensors network. The first stage of the proposed system consists of a multilabel deep neural network that makes a classification for each 4-s window. The second stage intelligently aggregates the classification results from the first stage of four neighboring nodes to determine the final classification result. Conducted experiments with real-world data and up to three different computing devices show that the system is able to provide classification results in less than 1 s and that it has good performance when classifying the most common events from the dataset. The results of this research may help civic organisations to obtain actionable noise monitoring information from automatic systems.

Citizen science can serve as a tool to obtain information about changes in the soundscape. One of the challenges of citizen science projects is the processing of data gathered by the citizens, to obtain conclusions. As part of the project Sons al Balcó, authors aim to study the soundscape in Catalonia during the lockdown due to the COVID-19 pandemic and afterwards and design a tool to automatically detect sound events as a first step to assess the quality of the soundscape. This paper details and compares the acoustic samples of the two collecting campaigns of the Sons al Balcó project. While the 2020 campaign obtained 365 videos, the 2021 campaign obtained 237. Later, a convolutional neural network is trained to automatically detect and classify acoustic events even if they occur simultaneously. Event based macro F1-score tops 50% for both campaigns for the most prevalent noise sources. However, results suggest that not all the categories are equally detected: the percentage of prevalence of an event in the dataset and its foregound-to-background ratio play a decisive role.

Analysing behavioural patterns of bird species in a certain region enables researchers to recognize forthcoming changes in environment, ecology, and population. Ornithologists spend many hours observing and recording birds in their natural habitat to compare different audio samples and extract valuable insights. This manual process is typically undertaken by highly-experienced birders that identify every species and its associated type of sound. In recent years, some public repositories hosting labelled acoustic samples from different bird species have emerged, which has resulted in appealing datasets that computer scientists can use to test the accuracy of their machine learning algorithms and assist ornithologists in the time-consuming process of analyzing audio data. Current limitations in the performance of these algorithms come from the fact that the acoustic samples of these datasets combine fragments with only environmental noise and fragments with the bird sound (i.e., the computer confuses environmental sound with the bird sound). Therefore, the purpose of this paper is to release a dataset lasting more than 4984 s that contains differentiated samples of (1) bird sounds and (2) environmental sounds. This data descriptor releases the processed audio samples—originally obtained from the Xeno-Canto repository—from the known seven families of the Picidae species inhabiting the Iberian Peninsula that are good indicators of the habitat quality and have significant value from the environment conservation point of view.