Overlapping Acoustic Event Detection via Perceptually Inspired the Holistic-based Representation Method

Choi H, Lee K, Keum M, Han D, Ko H. Overlapping Acoustic Event Detection via Perceptually Inspired the Holistic-based Representation Method. In: AES Convention 149. Audio Engineering Society; 2020. Paper 10395. Available from: https://aes.org/publications/elibrary-page/?id=20932

@inproceedings{Choi2020_20932,
  author = {Choi, Hyeonsik and Lee, Keunsang and Keum, Minseok and Han, David and Ko, Hanseok},
  title = {{Overlapping Acoustic Event Detection via Perceptually Inspired the Holistic-based Representation Method}},
  booktitle = {AES Convention 149},
  note = {Paper 10395},
  year = {2020},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=20932}
}

TY  - CPAPER
TI  - Overlapping Acoustic Event Detection via Perceptually Inspired the Holistic-based Representation Method
AU  - Choi, Hyeonsik
AU  - Lee, Keunsang
AU  - Keum, Minseok
AU  - Han, David
AU  - Ko, Hanseok
T2  - AES Convention 149
M1  - Paper 10395
SP  - 1
PY  - 2020
DA  - 2020/10/06
UR  - https://aes.org/publications/elibrary-page/?id=20932
PB  - Audio Engineering Society
LA  - en
AB  - A novel dictionary learning approach that utilizes Mel-scale frequency warping in detecting overlapped acoustic events is proposed. The study explored several dictionary learning schemes for improved performance of overlapping acoustic event detection. The structure of NMF for calculating gains of each event was utilized for including in overlapped signal for its low computational load. In this paper, we propose a method of frequency warping for better sound representation, and apply dictionary learning by a holistic-based representation, namely nonnegative K-SVD (NK-SVD) in order to resolve a basis sharing problem raised by part-based representations. By using Mel-scale in a dictionary learning, we show that the information carried by low frequency components more than high frequency components and dealt with a low complexity. Also, the proposed holistic-based representation method avoids the permutation problem between another acoustic events. Based on these benefits, we confirm that the proposed method of Mel-scale with NK-SVD delivered significantly better results than the conventional methods.
ER  -