TY - GEN
T1 - A Deep Neural Network-Driven Feature Learning Method for Polyphonic Acoustic Event Detection from Real-Life Recordings
AU - Mulimani, Manjunath
AU - Kademani, Akash B.
AU - Koolagudi, Shashidhar G.
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/5
Y1 - 2020/5
N2 - In this paper, a Deep Neural Network (DNN)-driven feature learning method for polyphonic Acoustic Event Detection (AED) is proposed. The proposed DNN is a combination of different layers used to characterize multiple overlapped acoustic events in the mixture. During training, DNN is able to learn the optimal set of discriminative spectral characteristics of the overlapped (polyphonic) acoustic events. The performance of the proposed method is evaluated on the TUT Sound Event 2016 (TUT-SED 2016) real-life dataset and joint Acoustic Scene Classification (ASC) and polyphonic AED dataset. Results show that proposed approach outperforms the state-of-the-art methods.
AB - In this paper, a Deep Neural Network (DNN)-driven feature learning method for polyphonic Acoustic Event Detection (AED) is proposed. The proposed DNN is a combination of different layers used to characterize multiple overlapped acoustic events in the mixture. During training, DNN is able to learn the optimal set of discriminative spectral characteristics of the overlapped (polyphonic) acoustic events. The performance of the proposed method is evaluated on the TUT Sound Event 2016 (TUT-SED 2016) real-life dataset and joint Acoustic Scene Classification (ASC) and polyphonic AED dataset. Results show that proposed approach outperforms the state-of-the-art methods.
UR - http://www.scopus.com/inward/record.url?scp=85089223618&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089223618&partnerID=8YFLogxK
U2 - 10.1109/ICASSP40776.2020.9054208
DO - 10.1109/ICASSP40776.2020.9054208
M3 - Conference contribution
AN - SCOPUS:85089223618
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 291
EP - 295
BT - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
Y2 - 4 May 2020 through 8 May 2020
ER -