Privacy-aware environmental sound classification for indoor human activity recognition

    Research output: Contribution to conferencePaper

    2 Citations (Scopus)
    108 Downloads (Pure)

    Abstract

    This paper presents a comparative study on dierent feature extraction and machine learning techniques for indoor environmental sound classication. Compared to outdoor environmental sound classication systems, indoor systems need to pay special attention to power consumption and privacy. We consider feature calculation complexity, classication accuracy and privacy as evaluation metrics. To ensure privacy, we strip voice bands from sound input to make human conversations unrecognizable. With 5 classes of 2500 indoor audio events as input, our experimental results show that using SVM model with LPCC feature, 78% classication accuracy can be reached. Furthermore, the performance is improved to more than 85% by combining several simple features and dropping unreliable predictions, which only slightly increase the complexity.

    Original languageEnglish
    Pages36-44
    Number of pages9
    DOIs
    Publication statusPublished - 5 Jun 2019
    Event12th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2019 - Rhodes, Greece
    Duration: 5 Jun 20197 Jun 2019
    Conference number: 12

    Conference

    Conference12th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2019
    Abbreviated titlePETRA 2019
    CountryGreece
    CityRhodes
    Period5/06/197/06/19

    Fingerprint Dive into the research topics of 'Privacy-aware environmental sound classification for indoor human activity recognition'. Together they form a unique fingerprint.

    Cite this