SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios
2026-07-02 • Sound
SoundArtificial Intelligence
AI summaryⓘ
The authors address the problem of finding where a specific sound is coming from when many sounds are happening at once. They created a system called SelectTSL that uses a special attention method to focus only on the sound the user wants, improving the direction estimates. Their approach also figures out how many sources of that target sound exist, even if this changes over time. Tests show their method works better than others and handles real-world noisy situations well.
sound source localizationselective attentionprompt-guidedinter-channel phase differencedirection of arrivaltarget sound extractionmultichannel audiodeep learningacoustic scene analysissource cardinality
Authors
Ziyang Jiang, Yu Chen, Zexu Pan, Xinyuan Qian, Bowen Xing, Ivor W. Tsang, Xu-Cheng Yin, Haizhou Li
Abstract
Humans can selectively attend to a target sound and estimate its direction in complex scenarios, whereas such selective localization remains challenging for current deep learning-based systems. Sound source localization (SSL) has achieved remarkable success with deep learning, yet most methods localize all active sources without selectivity. Conversely, target sound extraction (TSE) extracts sources using multimodal prompts but typically fails to preserve the multichannel spatial information required for accurate localization. To bridge this gap, we formulate the task of prompt-guided selective target sound localization and propose SelectTSL, an end-to-end architecture that localizes only the user-specified target in multi-source acoustic scenes. Specifically, we design a target-aware selective localization strategy that employs a Prompt-Guided Selective Attention Module (PGSA) to generate prompt-informed embeddings. These embeddings guide an inter-channel phase difference (IPD) enhancer to refine raw phase cues, fusing with target magnitudes to jointly estimate direction of arrival (DoA) and target-source cardinality, i.e., the number of target sound sources. This coupled design effectively focuses on the user-specified target spatial cues for selective localization and also handles time-varying numbers of target sources. Extensive experiments on both synthetic data and real-world recordings demonstrate that our proposed method consistently outperforms other baselines and exhibits robust generalization to real acoustic environments.