[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82644-en":3,"doc-seo-82644-105":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},82644,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","RT-Tango Real-Time Distributed Binaural Speech Enhancement for Low-Power Hearing Aid Devices","Real-time binaural speech enhancement is limited by latency, computational cost, and inter-device communication, while most efficient methods target single-channel scenarios. RT-Tango presents a real-time distributed binaural framework built for streaming on resource-constrained platforms, specifically hearing aids. It uses a two-stage architecture with perceptually motivated ERB feature compression, lightweight grouped recurrent mask estimation, and temporal sparsification. An asymmetric STFT decouples spectral resolution from algorithmic delay, enabling causal recurrent inference and online spatial-statistics estimation. Experiments show competitive enhancement with ultralow latency down to 8 ms and substantially reduced MAC operations.","RT-Tango: Real-Time Distributed Binaural Speech Enhancement for  \nLow-Power Hearing Aid Devices  \nZahra Benslimane  1 ,2, Pierre Chouteau 1, Martyna Poreba  1 , FabriceAuzanneau  1, Michal  \nSzczepanski  1, Fabian Chersi  1, Romain Serizel  2  \n1 Universit Paris-Saclay, CEA, List, F-91120 Palaiseau, France  \n2 Universit de Lorraine, CNRS, Inria, LORIA, F-54000 Nancy, France  \n[zahra-hafida.benslimane@cea.fr](zahra-hafida.benslimane@cea.fr)  \narXiv :2607 .0 1834v 1 [ cs . SD] 2 Jul 2026  \nAbstract  \nReal-time binaural speech enhancement is constrained by latency, computational cost, and inter-device communication, yet existing efficient solutions predominantly address singlechannel settings. In this paper, we introduce RT-Tango, areal-time distributed binaural speech enhancement framework designed for streaming on resource-constrained platforms and specifically for hearing aids. RT-Tango relies on a two-stage distributed architecture combining perceptually motivated ERB feature compression, lightweight grouped recurrent mask estimation, and temporal sparsification to reduce computational cost. Stringent latency constraints are addressed by decoupling spectral resolution from algorithmic delay using an asymmetric STFT, together with causal recurrent inference and online estimation of spatial statistics. Experimental results show that RT-Tango achieves competitive speech enhancement while significantly reducing MACs operations and functioning at ultralow latencies as low as 8 ms.  \nIndex Terms: speech enhancement, distributed, binaural, lowlatency, real-time, hearing aid  \n1. Introduction  \nReal-time speech enhancement (SE) in bandwidth-limited binaural and distributed systems, such as hearing aids, must operate under strict latency and computational constraints. Each device processes audio locally, exchanging only minimal information, which places strong limitations on model complexity and communication. Addressing SE under these joint constraints is essential for practical on-device deployment.  \nOne line of research focuses on reducing the computational cost of on-device SE through neural model compression, typically combining structured pruning and quantization to reduce memory use and computational complexity [1, 2, 3] . Hardwareoriented studies further show that not only the model’s sparsity level but also its structure critically impact the throughputmemory-quality trade-off on embedded platforms [4] . However, SE models are particularly sensitive to aggressive quantization due to their regression-based objectives, which amplifies quantization noise and hinders full integer deployment [5] . This has motivated the search for alternative solutions, such as hardware-aware mixed-precision inference [6] or distillationbased training strategies [7] . Complementary research explores architectural efficiency: designing compact models that inherently require fewer operations. Grouped processing is attractive for SE, where feature maps are partitioned into small groups and  \nThis research was carried out with the support of the French National Research Agency as part of the REFINED project,“REal-time artiFicial INtelligence for hEaring aiDs”(ANR21-CE19-0043) .  \nprocessed in parallel by tiny sub-networks that periodically exchange information [8, 9] . Other works reduce input dimensionality by sub-sampling [10] or using an Equivalent Rectangular Bandwidth (ERB)-scaled filterbank to compress the frequency representations, as in GTCRN [11] .  \nDespite these advances, most efficiency-driven approaches focus on single-microphone SE. In contrast, efficient multimicrophone methods remain comparatively underexplored, even though they can effectively exploit spatial cues for improved noise reduction. Recent works have begun to address this gap by proposing computationally efficient multimicrophone architectures, either by decoupling spatial and spectral processing [12] or by employing lightweight attention mechanisms to model spatial depend","cbCaimsFuRP5tKd0","https://ap.wps.com/l/cbCaimsFuRP5tKd0","pdf",317966,1,5,"English","en",105,"# Abstract\n# Introduction\n# Methodology","[{\"question\":\"What problem does RT-Tango address for hearing aids?\",\"answer\":\"RT-Tango targets real-time binaural speech enhancement under strict latency, computational, and distributed-communication constraints typical of hearing-aid systems.\"},{\"question\":\"What efficiency techniques does RT-Tango use in its architecture?\",\"answer\":\"It combines ERB-based perceptual feature compression, lightweight grouped recurrent mask estimation, and temporal sparsification to lower computational cost while maintaining streaming capability.\"},{\"question\":\"How does RT-Tango achieve low algorithmic delay in real time?\",\"answer\":\"It uses an asymmetric STFT configuration to decouple spectral resolution from algorithmic delay, together with causal recurrent inference and online estimation of spatial statistics.\"}]",1784182030,13,{"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},"rt-tango-real-time-distributed-binaural-speech-enhancement-for-low-power-hearing-aid-devices","",{"@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/rt-tango-real-time-distributed-binaural-speech-enhancement-for-low-power-hearing-aid-devices/82644/",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 RT-Tango address for hearing aids?","Question",{"text":75,"@type":76},"RT-Tango targets real-time binaural speech enhancement under strict latency, computational, and distributed-communication constraints typical of hearing-aid systems.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What efficiency techniques does RT-Tango use in its architecture?",{"text":80,"@type":76},"It combines ERB-based perceptual feature compression, lightweight grouped recurrent mask estimation, and temporal sparsification to lower computational cost while maintaining streaming capability.",{"name":82,"@type":73,"acceptedAnswer":83},"How does RT-Tango achieve low algorithmic delay in real time?",{"text":84,"@type":76},"It uses an asymmetric STFT configuration to decouple spectral resolution from algorithmic delay, together with causal recurrent inference and online estimation of spatial statistics.","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},[93,97,101,105,109,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":21,"slug":137},19,"General","general"]