StreamAAD: Decoding Spatial Auditory Attention with a Streaming Architecture
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_ | 1866917760021299200 |
|---|---|
| author | Qiu, Zelin Yao, Dingding Li, Junfeng |
| author_facet | Qiu, Zelin Yao, Dingding Li, Junfeng |
| contents | In this paper, we present our approach for the Track 1 of the Chinese Auditory Attention Decoding (Chinese AAD) Challenge at ISCSLP 2024. Most existing spatial auditory attention decoding (Sp-AAD) methods employ an isolated window architecture, focusing solely on global invariant features without considering relationships between different decision windows, which can lead to suboptimal performance. To address this issue, we propose a novel streaming decoding architecture, termed StreamAAD. In StreamAAD, decision windows are input to the network as a sequential stream and decoded in order, allowing for the modeling of inter-window relationships. Additionally, we employ a model ensemble strategy, achieving significant better performance than the baseline, ranking First in the challenge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_13522 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | StreamAAD: Decoding Spatial Auditory Attention with a Streaming Architecture Qiu, Zelin Yao, Dingding Li, Junfeng Sound Audio and Speech Processing In this paper, we present our approach for the Track 1 of the Chinese Auditory Attention Decoding (Chinese AAD) Challenge at ISCSLP 2024. Most existing spatial auditory attention decoding (Sp-AAD) methods employ an isolated window architecture, focusing solely on global invariant features without considering relationships between different decision windows, which can lead to suboptimal performance. To address this issue, we propose a novel streaming decoding architecture, termed StreamAAD. In StreamAAD, decision windows are input to the network as a sequential stream and decoded in order, allowing for the modeling of inter-window relationships. Additionally, we employ a model ensemble strategy, achieving significant better performance than the baseline, ranking First in the challenge. |
| title | StreamAAD: Decoding Spatial Auditory Attention with a Streaming Architecture |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2408.13522 |