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

arXiv: https://arxiv.org/abs/2110.07124 · HTML: https://mlsanity.com/paper/2110.07124/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2021.

## Built on by (most cited first, 25 of 25)

- [STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events](https://mlsanity.com/paper/2306.09126/) (2023)
- [Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation](https://mlsanity.com/paper/2410.10676/) (2024)
- [Sound Event Detection and Localization with Distance Estimation](https://mlsanity.com/paper/2403.11827/) (2024)
- [Spatial Scaper: A Library to Simulate and Augment Soundscapes for Sound Event Localization and Detection in Realistic Rooms](https://mlsanity.com/paper/2401.12238/) (2024)
- [The World is Not Mono: Enabling Spatial Understanding in Large Audio-Language Models](https://mlsanity.com/paper/2601.02954/) (2026)
- [Sci-Phi: A Large Language Model Spatial Audio Descriptor](https://mlsanity.com/paper/2510.05542/) (2025)
- [Robust detection of overlapping bioacoustic sound events](https://mlsanity.com/paper/2503.02389/) (2025)
- [Stereo Sound Event Localization and Detection with Onscreen/offscreen Classification](https://mlsanity.com/paper/2507.12042/) (2025)
- [Position tracking of a varying number of sound sources with sliding permutation invariant training](https://mlsanity.com/paper/2210.14536/) (2022)
- [Enhanced Sound Event Localization and Detection in Real 360-degree audio-visual soundscapes](https://mlsanity.com/paper/2401.17129/) (2024)
- [Leveraging Reverberation and Visual Depth Cues for Sound Event Localization and Detection with Distance Estimation](https://mlsanity.com/paper/2410.22271/) (2024)
- [Semantic Audio-Visual Navigation in Continuous Environments](https://mlsanity.com/paper/2603.19660/) (2026)
- [Spatio-Temporal Audio Language Modeling for Dynamic Sound Sources](https://mlsanity.com/paper/2606.14141/) (2026)
- [MFF-EINV2: Multi-scale Feature Fusion across Spectral-Spatial-Temporal Domains for Sound Event Localization and Detection](https://mlsanity.com/paper/2406.08771/) (2024)
- [Learning Multi-Target TDOA Features for Sound Event Localization and Detection](https://mlsanity.com/paper/2408.17166/) (2024)
- [Spatial and Semantic Embedding Integration for Stereo Sound Event Localization and Detection in Regular Videos](https://mlsanity.com/paper/2507.04845/) (2025)
- [Latent Acoustic Mapping for Direction of Arrival Estimation: A Self-Supervised Approach](https://mlsanity.com/paper/2507.07066/) (2025)
- [Integrating Spatial and Semantic Embeddings for Stereo Sound Event Localization in Videos](https://mlsanity.com/paper/2509.06598/) (2025)
- [SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios](https://mlsanity.com/paper/2607.02343/) (2026)
- [CoLoC: Conditioned Localizer and Classifier for Sound Event Localization and Detection](https://mlsanity.com/paper/2210.13932/) (2022)
- [DOA-Aware Audio-Visual Self-Supervised Learning for Sound Event Localization and Detection](https://mlsanity.com/paper/2410.22803/) (2024)
- [An Experimental Study on Joint Modeling for Sound Event Localization and Detection with Source Distance Estimation](https://mlsanity.com/paper/2501.10755/) (2025)
- [EquiSELD: Efficient training of equivariant sound event localization and detection networks](https://mlsanity.com/paper/2609.23156/) (2026)
- [SEA-LM: Egocentric Spatial Audio Understanding for Wearable Microphone Arrays](https://mlsanity.com/paper/2610.05610/) (2026)
- [SonicWorld: Source-Centric Latent Dynamics for Spatial Audio Reasoning](https://mlsanity.com/paper/2610.17131/) (2026)

## Abstract (arXiv)

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.