# CST-former: Transformer with Channel-Spectro-Temporal Attention for Sound Event Localization and Detection

arXiv: https://arxiv.org/abs/2312.12821 · HTML: https://mlsanity.com/paper/2312.12821/

## Key facts

- Cited by 8 papers in the map (data through 13 Oct 2026).
- First posted on arXiv 20 Dec 2023.

## Built on by (most cited first, 8 of 8)

- [SONICS: Synthetic Or Not -- Identifying Counterfeit Songs](https://mlsanity.com/paper/2408.14080/) (2024)
- [SELD-Mamba: Selective State-Space Model for Sound Event Localization and Detection with Source Distance Estimation](https://mlsanity.com/paper/2408.05057/) (2024)
- [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)
- [SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios](https://mlsanity.com/paper/2607.02343/) (2026)
- [An Experimental Study on Joint Modeling for Sound Event Localization and Detection with Source Distance Estimation](https://mlsanity.com/paper/2501.10755/) (2025)
- [ESTM: An Enhanced Dual-Branch Spectral-Temporal Mamba for Anomalous Sound Detection](https://mlsanity.com/paper/2509.02471/) (2025)
- [Cooperative Multi-Agent Reinforcement Learning for Adaptive Aggregation in Semi-Supervised Federated Learning with non-IID Data](https://mlsanity.com/paper/2608.25794/) (2026)

## Abstract (arXiv)

Sound event localization and detection (SELD) is a task for the classification of sound events and the localization of direction of arrival (DoA) utilizing multichannel acoustic signals. Prior studies employ spectral and channel information as the embedding for temporal attention. However, this usage limits the deep neural network from extracting meaningful features from the spectral or spatial domains. Therefore, our investigation in this paper presents a novel framework termed the Channel-Spectro-Temporal Transformer (CST-former) that bolsters SELD performance through the independent application of attention mechanisms to distinct domains. The CST-former architecture employs distinct attention mechanisms to independently process channel, spectral, and temporal information. In addition, we propose an unfolded local embedding (ULE) technique for channel attention (CA) to generate informative embedding vectors including local spectral and temporal information. Empirical validation through experimentation on the 2022 and 2023 DCASE Challenge task3 datasets affirms the efficacy of employing attention mechanisms separated across each domain and the benefit of ULE, in enhancing SELD performance.