[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82663-en":3,"doc-seo-82663-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82663,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","SelectTSL Prompt-Guided Selective Target Sound Localization in Complex Scenarios","Prompt-guided selective target sound localization remains difficult for deep learning systems because existing sound source localization (SSL) typically localizes all active sources without selectivity, while target sound extraction (TSE) often loses the multichannel spatial cues needed for direction estimation. SelectTSL formulates an end-to-end task to localize only user-specified targets in multi-source acoustic scenes. A Prompt-Guided Selective Attention Module (PGSA) generates prompt-informed embeddings, which guide an IPD enhancer to refine phase cues and jointly estimate DoA and target-source cardinality, achieving robust generalization on synthetic and real recordings.","SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios  \nZiyang Jiang, Student Member, IEEE, Yu Chen, Zexu Pan, Member, IEEE, Xinyuan Qian, Senior Member, IEEE, Bowen Xing, Ivor W. Tsang, Fellow, IEEE, Xu-Cheng Yin, Senior Member, IEEE, Haizhou Li, Fellow, IEEE  \narXiv :2607 .02343v 1 [ cs . SD] 2 Jul 2026  \nAbstract—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 an 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. Dataset and code will be released.  \nI. INTRODUCTION  \nSOUND source localization (SSL), which estimates the  \nspatial location of acoustic events, supports a wide range of array-based audio and speech applications. For instance, in smart speakers, SSL enables direction-aware target speech enhancement and far-field automatic speech recognition (ASR) by steering microphone-array beamformers [1] . In hearing aids, it supports directional noise reduction via spatial filtering [2] . Despite remarkable progress of SSL via signal processing (e.g., generalized cross-correlation with phase transform (GCC-PHAT) [3], multiple signal classification (MUSIC) [4]) or deep neural networks (e.g., convolutional recurrent neural networks (CRNNs) [5]), existing methods are inherently semantic-blind, treating all acoustic sources as generic signals without identity awareness: all active sources are localized without selectivity, including interfering sounds. This differs from human auditory perception where listeners can selectively attend to a target sound when competing speakers and background noise exist, i.e., the “cocktail party problem”  \n[6] . As illustrated in Fig. 1(a), conventional SSL systems indiscriminately localize both target and irrelevant sources (e.g., dog barks and noise), yielding non-selective direction-ofarrival (DoA) trajectories and preventing users from directing the system to focus on a specific target such as speech.  \nFig. 1. Illustration of conventional semantic-blind SSL and our proposed prompt-guided SelectTSL: (a) Conventional SSL localizes all active sources, yielding non-selective DoA trajectories, whereas (b) SelectTSL uses a text and audio prompt (“locate the speech”) to focus on the target speech which only provides its corresponding DoA trajectory.  \nTo associate semantics with location, sound event localization and detection (SELD) methods [7], [7], [8] detect and localize all events of known classes. However, they perform passive scene analysis that lacks an interactive mechanism to filter sources based on user intent [9] . Conversely, i","cbCaivETkbCvP8MY","https://ap.wps.com/l/cbCaivETkbCvP8MY","pdf",1452615,1,15,"English","en",105,"# Introduction\n## Motivation: semantic-blind SSL and the cocktail-party gap\n## Related work: SELD and target sound extraction\n## Proposed SelectTSL framework\n## Contributions and task formulation","[{\"question\":\"What problem does SelectTSL address in complex multi-source acoustic scenes?\",\"answer\":\"SelectTSL targets the lack of selectivity in current SSL systems, which localize all active sources, and the spatial-cue degradation in TSE methods that prevents accurate localization.\"},{\"question\":\"How does SelectTSL use prompts to achieve selective localization?\",\"answer\":\"SelectTSL employs a Prompt-Guided Selective Attention Module (PGSA) conditioned on multimodal prompts (text or audio) to generate prompt-informed embeddings that act as a semantic filter for the target.\"},{\"question\":\"What spatial cues does SelectTSL refine to estimate direction of arrival?\",\"answer\":\"An inter-channel phase difference (IPD) enhancer refines raw phase cues, and the refined spatial features are fused with target magnitudes to jointly estimate DoA.\"}]",1784182151,38,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"selecttsl-prompt-guided-selective-target-sound-localization-in-complex-scenarios","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/selecttsl-prompt-guided-selective-target-sound-localization-in-complex-scenarios/82663/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does SelectTSL address in complex multi-source acoustic scenes?","Question",{"text":75,"@type":76},"SelectTSL targets the lack of selectivity in current SSL systems, which localize all active sources, and the spatial-cue degradation in TSE methods that prevents accurate localization.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does SelectTSL use prompts to achieve selective localization?",{"text":80,"@type":76},"SelectTSL employs a Prompt-Guided Selective Attention Module (PGSA) conditioned on multimodal prompts (text or audio) to generate prompt-informed embeddings that act as a semantic filter for the target.",{"name":82,"@type":73,"acceptedAnswer":83},"What spatial cues does SelectTSL refine to estimate direction of arrival?",{"text":84,"@type":76},"An inter-channel phase difference (IPD) enhancer refines raw phase cues, and the refined spatial features are fused with target magnitudes to jointly estimate DoA.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]