An acoustic monitoring system and its field trials

Komatsu, Tatsuya; Tani, Masanori; Toizumi, Takahiro; Narisetty, Chaitanya; Kato, Masashi; Arai, Yumi; Hoshuyama, Osamu; Senda, Yuzo; Kondo, Reishi

doi:10.1109/apsipa.2017.8282240

Cited by 3 publications

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar but hidden imbalance among the exemplars of an individual sound event was observed in NEC's field trials [10]. For the purpose of illustration, consider a Piano sound event consisting of 10 exemplars for 3 notes C4-G4-E4 played simultaneously for 1 second and only 1 exemplar for a C4 note played for 0.5 seconds.…”

Section: Introductionmentioning

confidence: 65%

Modelling of Sound Events with Hidden Imbalances Based on Clustering and Separate Sub-Dictionary Learning

Narisetty

Komatsu

Kondo

2018

2018 26th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

This paper proposes an effective modelling of sound event spectra with a hidden data-size-imbalance, for improved Acoustic Event Detection (AED). The proposed method models each event as an aggregated representation of a few latent factors, while conventional approaches try to find acoustic elements directly from the event spectra. In the method, all the latent factors across all events are assigned comparable importance and complexity to overcome the hidden imbalance of data-sizes in event spectra. To extract latent factors in each event, the proposed method employs clustering and performs non-negative matrix factorization to each latent factor, and learns its acoustic elements as a sub-dictionary. Separate sub-dictionary learning effectively models the acoustic elements with limited data-sizes and avoids over-fitting due to hidden imbalances in training data. For the task of polyphonic sound event detection from DCASE 2013 challenge, an AED based on the proposed modelling achieves a detection F-measure of 46.5%, a significant improvement of more than 19% as compared to the existing state-of-the-art methods.

show abstract

Section: Introductionmentioning

confidence: 65%