TY - GEN
T1 - Weakly Supervised Source-Specific Sound Level Estimation in Noisy Soundscapes
AU - Cramer, Aurora
AU - Cartwright, Mark
AU - Pishdadian, Fatemeh
AU - Bello, Juan Pablo
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - While the estimation of what sound sources are, when they occur, and from where they originate has been well-studied, the estimation of how loud these sound sources are has been often overlooked. Current solutions to this task, which we refer to as source-specific sound level estimation (SSSLE), suffer from challenges due to the impracticality of acquiring realistic data and a lack of robustness to realistic recording conditions. Recently proposed weakly supervised source separation offer a means of leveraging clip-level source annotations to train source separation models, which we augment with modified loss functions to bridge the gap between source separation and SSSLE and to address the presence of background. We show that our approach improves SSSLE performance compared to baseline source separation models and provide an ablation analysis to explore our method's design choices, showing that SSSLE in practical recording and annotation scenarios is possible.
AB - While the estimation of what sound sources are, when they occur, and from where they originate has been well-studied, the estimation of how loud these sound sources are has been often overlooked. Current solutions to this task, which we refer to as source-specific sound level estimation (SSSLE), suffer from challenges due to the impracticality of acquiring realistic data and a lack of robustness to realistic recording conditions. Recently proposed weakly supervised source separation offer a means of leveraging clip-level source annotations to train source separation models, which we augment with modified loss functions to bridge the gap between source separation and SSSLE and to address the presence of background. We show that our approach improves SSSLE performance compared to baseline source separation models and provide an ablation analysis to explore our method's design choices, showing that SSSLE in practical recording and annotation scenarios is possible.
KW - machine listening
KW - sound event recognition
KW - source separation
KW - source-specific sound level estimation
KW - weakly supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85123451340&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85123451340&partnerID=8YFLogxK
U2 - 10.1109/WASPAA52581.2021.9632767
DO - 10.1109/WASPAA52581.2021.9632767
M3 - Conference contribution
AN - SCOPUS:85123451340
T3 - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
SP - 61
EP - 65
BT - 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021
Y2 - 17 October 2021 through 20 October 2021
ER -