Multi-ACCDOA: Localizing and Detecting Overlapping Sounds from the Same Class with Auxiliary Duplicating Permutation Invariant Training

10/14/2021
by   Kazuki Shimada, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/19/2022

A Track-Wise Ensemble Event Independent Network for Polyphonic Sound Event Localization and Detection

Polyphonic sound event localization and detection (SELD) aims at detecti...
research
09/30/2020

Event-Independent Network for Polyphonic Sound Event Localization and Detection

Polyphonic sound event localization and detection is not only detecting ...
research
10/25/2020

An Improved Event-Independent Network for Polyphonic Sound Event Localization and Detection

Polyphonic sound event localization and detection (SELD), which jointly ...
research
10/17/2019

Unshuffling fields in data formats

Data format reverse engineering commonly involves identifying conserved ...
research
09/05/2022

Sound Event Localization and Detection for Real Spatial Sound Scenes: Event-Independent Network and Data Augmentation Chains

Sound event localization and detection (SELD) is a joint task of sound e...
research
10/29/2020

ACCDOA: Activity-Coupled Cartesian Direction of Arrival Representation for Sound Event Localization and Detection

Neural-network (NN)-based methods show high performance in sound event l...
research
09/17/2023

Zero- and Few-shot Sound Event Localization and Detection

Sound event localization and detection (SELD) systems estimate direction...

Please sign up or login with your details

Forgot password? Click here to reset