# L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environment

arXiv: https://arxiv.org/abs/2202.10372 · HTML: https://mlsanity.com/paper/2202.10372/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 21 Feb 2022.

## Builds on (most cited first, 17 of 17)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://mlsanity.com/paper/2010.00475/) (2020)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks](https://mlsanity.com/paper/1807.00129/) (2018)
- [Overview and Evaluation of Sound Event Localization and Detection in DCASE 2019](https://mlsanity.com/paper/2009.02792/) (2020)
- [FaSNet: Low-latency Adaptive Beamforming for Multi-microphone Audio Processing](https://mlsanity.com/paper/1909.13387/) (2019)
- [A Dataset of Reverberant Spatial Sound Scenes with Moving Sources for Sound Event Localization and Detection](https://mlsanity.com/paper/2006.01919/) (2020)
- [Polyphonic Sound Event Detection and Localization using a Two-Stage Strategy](https://mlsanity.com/paper/1905.00268/) (2019)
- [Sound Event Detection Using Spatial Features and Convolutional Recurrent Neural Network](https://mlsanity.com/paper/1706.02291/) (2017)
- [First Order Ambisonics Domain Spatial Augmentation for DNN-based Direction of Arrival Estimation](https://mlsanity.com/paper/1910.04388/) (2019)
- [L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processing](https://mlsanity.com/paper/2104.05499/) (2021)
- [SELD-TCN: Sound Event Localization & Detection via Temporal Convolutional Networks](https://mlsanity.com/paper/2003.01609/) (2020)
- [Discriminative Learning for Monaural Speech Separation Using Deep Embedding Features](https://mlsanity.com/paper/1907.09884/) (2019)
- [DBNET: DOA-driven beamforming network for end-to-end farfield sound source separation](https://mlsanity.com/paper/2010.11566/) (2020)
- [Multichannel Sound Event Detection Using 3D Convolutional Neural Networks for Learning Inter-channel Features](https://mlsanity.com/paper/1801.09522/) (2018)
- [An Iterative Graph Spectral Subtraction Method for Speech Enhancement](https://mlsanity.com/paper/2006.08497/) (2020)

## Built on by (most cited first, 10 of 10)

- [BAT: Learning to Reason about Spatial Sounds with Large Language Models](https://mlsanity.com/paper/2402.01591/) (2024)
- [Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization](https://mlsanity.com/paper/2505.11217/) (2025)
- [Dual Quaternion Ambisonics Array for Six-Degree-of-Freedom Acoustic Representation](https://mlsanity.com/paper/2204.01851/) (2022)
- [ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding](https://mlsanity.com/paper/2207.09514/) (2022)
- [FolAI: Synchronized Foley Sound Generation with Semantic and Temporal Alignment](https://mlsanity.com/paper/2412.15023/) (2024)
- [Overview of the L3DAS23 Challenge on Audio-Visual Extended Reality](https://mlsanity.com/paper/2402.09245/) (2024)
- [Dual input neural networks for positional sound source localization](https://mlsanity.com/paper/2308.04169/) (2023)
- [D4AM: A General Denoising Framework for Downstream Acoustic Models](https://mlsanity.com/paper/2311.16595/) (2023)
- [SoundLoc3D: Invisible 3D Sound Source Localization and Classification Using a Multimodal RGB-D Acoustic Camera](https://mlsanity.com/paper/2412.16861/) (2024)
- [Supervising Sound Localization by In-the-wild Egomotion](https://mlsanity.com/paper/2610.01388/) (2026)

## Abstract (arXiv)

The L3DAS22 Challenge is aimed at encouraging the development of machine learning strategies for 3D speech enhancement and 3D sound localization and detection in office-like environments. This challenge improves and extends the tasks of the L3DAS21 edition. We generated a new dataset, which maintains the same general characteristics of L3DAS21 datasets, but with an extended number of data points and adding constrains that improve the baseline model's efficiency and overcome the major difficulties encountered by the participants of the previous challenge. We updated the baseline model of Task 1, using the architecture that ranked first in the previous challenge edition. We wrote a new supporting API, improving its clarity and ease-of-use. In the end, we present and discuss the results submitted by all participants. L3DAS22 Challenge website: www.l3das.com/icassp2022.