On Multitask Loss Function for Audio Event Detection and Localization

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.

Accepted for publication in DCASE 2020 Workshop

References in corpus (5)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection
• Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks
• A Dataset of Reverberant Spatial Sound Scenes with Moving Sources for Sound Event Localization and Detection

Cited by in corpus (5)

• A Survey of Sound Source Localization with Deep Learning Methods
• SALSA: Spatial Cue-Augmented Log-Spectrogram Features for Polyphonic Sound Event Localization and Detection
• A Dataset of Dynamic Reverberant Sound Scenes with Directional Interferers for Sound Event Localization and Detection
• ACCDOA: Activity-Coupled Cartesian Direction of Arrival Representation for Sound Event Localization and Detection
• A General Network Architecture for Sound Event Localization and Detection Using Transfer Learning and Recurrent Neural Network