DOA-Aware Audio-Visual Self-Supervised Learning for Sound Event Localization and Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916461053739008 |
|---|---|
| author | Fujita, Yoto Bando, Yoshiaki Imoto, Keisuke Onishi, Masaki Yoshii, Kazuyoshi |
| author_facet | Fujita, Yoto Bando, Yoshiaki Imoto, Keisuke Onishi, Masaki Yoshii, Kazuyoshi |
| contents | This paper describes sound event localization and detection (SELD) for spatial audio recordings captured by firstorder ambisonics (FOA) microphones. In this task, one may train a deep neural network (DNN) using FOA data annotated with the classes and directions of arrival (DOAs) of sound events. However, the performance of this approach is severely bounded by the amount of annotated data. To overcome this limitation, we propose a novel method of pretraining the feature extraction part of the DNN in a self-supervised manner. We use spatial audio-visual recordings abundantly available as virtual reality contents. Assuming that sound objects are concurrently observed by the FOA microphones and the omni-directional camera, we jointly train audio and visual encoders with contrastive learning such that the audio and visual embeddings of the same recording and DOA are made close. A key feature of our method is that the DOA-wise audio embeddings are jointly extracted from the raw audio data, while the DOA-wise visual embeddings are separately extracted from the local visual crops centered on the corresponding DOA. This encourages the latent features of the audio encoder to represent both the classes and DOAs of sound events. The experiment using the DCASE2022 Task 3 dataset of 20 hours shows non-annotated audio-visual recordings of 100 hours reduced the error score of SELD from 36.4 pts to 34.9 pts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_22803 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DOA-Aware Audio-Visual Self-Supervised Learning for Sound Event Localization and Detection Fujita, Yoto Bando, Yoshiaki Imoto, Keisuke Onishi, Masaki Yoshii, Kazuyoshi Sound Artificial Intelligence Machine Learning Multimedia Audio and Speech Processing This paper describes sound event localization and detection (SELD) for spatial audio recordings captured by firstorder ambisonics (FOA) microphones. In this task, one may train a deep neural network (DNN) using FOA data annotated with the classes and directions of arrival (DOAs) of sound events. However, the performance of this approach is severely bounded by the amount of annotated data. To overcome this limitation, we propose a novel method of pretraining the feature extraction part of the DNN in a self-supervised manner. We use spatial audio-visual recordings abundantly available as virtual reality contents. Assuming that sound objects are concurrently observed by the FOA microphones and the omni-directional camera, we jointly train audio and visual encoders with contrastive learning such that the audio and visual embeddings of the same recording and DOA are made close. A key feature of our method is that the DOA-wise audio embeddings are jointly extracted from the raw audio data, while the DOA-wise visual embeddings are separately extracted from the local visual crops centered on the corresponding DOA. This encourages the latent features of the audio encoder to represent both the classes and DOAs of sound events. The experiment using the DCASE2022 Task 3 dataset of 20 hours shows non-annotated audio-visual recordings of 100 hours reduced the error score of SELD from 36.4 pts to 34.9 pts. |
| title | DOA-Aware Audio-Visual Self-Supervised Learning for Sound Event Localization and Detection |
| topic | Sound Artificial Intelligence Machine Learning Multimedia Audio and Speech Processing |
| url | https://arxiv.org/abs/2410.22803 |