Multi-ACCDOA: Localizing And Detecting Overlapping Sounds From The Same Class With Auxiliary Duplicating Permutation Invariant Training
Authors:
- 23 May 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 316-320
Abstract
Sound event localization and detection (SELD) involves identifying the direction-of-arrival (DOA) and the event class. The SELD methods with a class-wise output format make the model predict activities of all sound event classes and corresponding locations. The class-wise methods can output activity-coupled Cartesian DOA (ACCDOA) vectors, which enable us to solve a SELD task with a single target using a single network. However, there is still a challenge in detecting the same event class from multiple locations. To overcome this problem while maintaining the advantages of the class-wise format, we extended ACCDOA to a multi one and proposed auxiliary duplicating permutation invariant training (ADPIT). The multi-ACCDOA format (a class- and track-wise output format) enables the model to solve the cases with overlaps from the same class. The class-wise ADPIT scheme enables each track of the multi-ACCDOA format to learn with the same target as the single-ACCDOA format. In evaluations with the DCASE 2021 Task 3 dataset, the model trained with the multi-ACCDOA format and with the class-wise ADPIT detects overlapping events from the same class while maintaining its performance in the other cases. Also, the proposed method performed comparably to state-of-the-art SELD methods with fewer parameters.Keywords
This publication has 15 references indexed in Scilit:
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition2019
- Polyphonic Sound Event Detection and Localization using a Two-Stage Strategy2019
- Investigations on Data Augmentation and Loss Functions for Deep Learning Based Speech-Background Separation2018
- Multi-Channel Deep Clustering: Discriminative Spectral and Spatial Embeddings for Speaker-Independent Speech Separation2018
- AENet: Learning Deep Audio Features for Video AnalysisIEEE Transactions on Multimedia, 2017
- Multitalker Speech Separation With Utterance-Level Permutation Invariant Training of Deep Recurrent Neural NetworksIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2017
- Sound Source Localization Using Deep Learning ModelsJournal of Robotics and Mechatronics, 2017
- Audio SurveillanceACM Computing Surveys, 2016
- Environmental Sound Recognition With Time–Frequency Audio FeaturesIEEE Transactions on Audio, Speech, and Language Processing, 2009
- Scream and gunshot detection and localization for audio-surveillance systems2007