Environmental sound monitoring using machine learning on mobile devices

Green, Marc; Murphy, Damian

doi:10.1016/j.apacoust.2019.107041

Cited by 28 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The importance of these areas for health protection and promotion is quite obvious, as they are potentially well suited to the needs of citizens of metropolitan areas in relieving stress and improving feelings of well-being. Further interesting developments will deal with analysis of tags used in social networks to describe everyday acoustic environments and/or pictures of places, and machine learning techniques for sound categorization in terms of perception [93,94].…”

Section: Discussionmentioning

confidence: 99%

Smartphone-Based Participatory Soundscape Mapping for a More Sustainable Acoustic Environment

Brambilla

Pedrielli

2020

Sustainability

View full text Add to dashboard Cite

The urban environmental planning, a fundamental dynamic process for cities’ sustainability, could benefit from the soundscape approach, dealing with the perception of the acoustic environment in which sound is considered as a resource rather than a waste (noise). Noise and soundscape maps are useful tools for planning mitigation actions and for communication with citizens. Both mappings can benefit from crowdsourcing and participatory sound monitoring that has been made possible due to the large use of internet connections and mobile devices with dedicated apps. This paper is a “scoping review” to provide an overview of the potential, benefits, and drawbacks of participatory noise monitoring in noise and soundscape mapping applications, while also referring to metrological aspects. Gathering perceptual data on soundscapes by using digital questionnaires will likely be more commonly used than printed questionnaires; thus, the main differences between the experimental protocols concern the measurement of acoustic data. The authors propose to classify experimental protocols for in-field soundscape surveys into three types (GUIDE, MONITOR, and SMART) to be selected according to the survey’s objectives and the territorial extension. The main future developments are expected to be related to progress in smartphone hardware and software, to the growth of social networks data analysis, as well as to the implementation of machine learning techniques.

show abstract

Section: Discussionmentioning

confidence: 99%

Smartphone-Based Participatory Soundscape Mapping for a More Sustainable Acoustic Environment

Brambilla

Pedrielli

2020

Sustainability

View full text Add to dashboard Cite

show abstract

“…Audio textures and its associated features, such as LBP and HOG, are used in ASA [106]. In many application MFCCs have been used for ASA [107]. Recently deep learning algorithms have taken the TFR of the textural audio as an image and performed various classification tasks [32,33,108,24,109,110].…”

Section: Applications Of Audio Texturesmentioning

confidence: 99%

Trends in Audio Texture Analysis, Synthesis, and Applications

Sharma¹,

Umapathy²

2022

J. Audio Eng. Soc.

View full text Add to dashboard Cite

Audio signals are classified into speech, music, and environmental sounds. From the evolution of audio features, an adequate amount of work has been seen in speech and music processing. On the other hand, the environmental sounds have not been studied that much, and the major reason behind it is the lack of coherent information present in an environmental sound compared with the speech signal or a musical sound. The definition to express audio textures is imprecise and insufficient, so audio textures tend to be defined by drawing a comparison to the known sound source (e.g., "it sounds like a motor" or "like a fan"). Audio textures could be either natural or artificial. Natural audio textures, such as heavy rain, fire, and stream flowing, are very common. The artificial audio textures include sounds such as applause, a motor running, someone walking on gravel, babble, and many more. Although these audio textures have been used in virtual reality, music, screen saver sounds, and more, a considerable amount of possible work is still untouched. The aim of this study is to summarize the literature on audio textures, textural features, and their applications. In this survey, the texture synthesis and features are explained in detail.

show abstract

“…Thus, the MFCC coefficients retrieves data related to the sound as a short-term power spectrum composed by a linear cosine transform of a log power spectrum on a nonlinear Mel-scale of frequency, which, as previously used in other studies, e.g. , [7 , 13] , it consists in the codification of audio data for the identification of the different frequencies. It allows the categorization of the different data collected, because it discretizes the data for the correct identification.…”

Section: Data Descriptionmentioning

confidence: 99%

Indoor and outdoor environmental data: A dataset with acoustic data acquired by the microphone embedded on mobile devices

Pires

García²,

Zdravevski³

et al. 2021

Data in Brief

View full text Add to dashboard Cite

All mobile devices include a microphone that can be used for acoustic data acquisition. This article presents a dataset of acoustic signals related to nine environments, captured with a microphone embedded on off-the-shelf mobile devices. The mobile phone can be placed in the pants pockets, in a wristband, over the bedside table, on a table, or on other furniture. Data collection environments are bar, classroom, gym, kitchen, library, street, hall, living room, and bedroom. The data was collected by 25 individuals (15 men and 10 women) in different environments around Covilhã and Fundão municipalities (Portugal). The microphone data was sampled with 44,100 Hz into an array with 16-bit unsigned integer values in the range [0, 255] with a 128 offset for zero. The dataset presented in this paper presents at least 2000 samples of 5 s of data for each environment, corresponding to around 2.8 h for each environment into text files. In total, it includes at least 25.2 h of acoustic data for the implementation of data processing techniques, e.g., Fast Fourier Transform (FFT), and other machine learning methods for the different analysis.

show abstract

Environmental sound monitoring using machine learning on mobile devices

Cited by 28 publications

References 17 publications

Smartphone-Based Participatory Soundscape Mapping for a More Sustainable Acoustic Environment

Smartphone-Based Participatory Soundscape Mapping for a More Sustainable Acoustic Environment

Trends in Audio Texture Analysis, Synthesis, and Applications

Indoor and outdoor environmental data: A dataset with acoustic data acquired by the microphone embedded on mobile devices

Contact Info

Product

Resources

About