Abstract
Audio event localization and detection (SELD) have been commonly tackled using multitask models. Such a model usually consists of a multi-label event classification branch
with sigmoid cross-entropy loss for event activity detection and a regression branch with mean squared error loss for direction-of-arrival estimation. In this work, we propose a
multitask regression model, in which both (multi-label) event detection and localization are formulated as regression problems and use the mean squared error loss homogeneously for
model training. We show that the common combination of heterogeneous loss functions causes the network to underfit the data whereas the homogeneous mean squared error loss
leads to better convergence and performance. Experiments on the development and validation sets of the DCASE 2020 SELD task demonstrate that the proposed system also outperforms the DCASE 2020 SELD baseline across all the detection and localization metrics, reducing the overall SELD error (the combined metric) by approximately 10% absolute.
with sigmoid cross-entropy loss for event activity detection and a regression branch with mean squared error loss for direction-of-arrival estimation. In this work, we propose a
multitask regression model, in which both (multi-label) event detection and localization are formulated as regression problems and use the mean squared error loss homogeneously for
model training. We show that the common combination of heterogeneous loss functions causes the network to underfit the data whereas the homogeneous mean squared error loss
leads to better convergence and performance. Experiments on the development and validation sets of the DCASE 2020 SELD task demonstrate that the proposed system also outperforms the DCASE 2020 SELD baseline across all the detection and localization metrics, reducing the overall SELD error (the combined metric) by approximately 10% absolute.
| Original language | English |
|---|---|
| Title of host publication | Detection and Classification of Acoustic Scenes and Events (DCASE), 2020 |
| Pages | 160-164 |
| Publication status | Published - Nov 2020 |
| Event | Detection and Classification of Acoustic Scenes and Events 2020 - Tokyo, Japan, Tokyo, Japan Duration: 2 Nov 2020 → 3 Nov 2020 |
Other
| Other | Detection and Classification of Acoustic Scenes and Events 2020 |
|---|---|
| Country/Territory | Japan |
| City | Tokyo |
| Period | 2/11/20 → 3/11/20 |
Research Field
- Former Research Field - Data Science