Subject: [AUDITORY] DCASE Workshop 2026: Second Call for Paper From: Aleksandra Teng Ma <tengofma@xxxxxxxx> Date: Thu, 4 Jun 2026 19:14:01 -0400--000000000000d65213065375b397 Content-Type: text/plain; charset="UTF-8" ******* Apologies for cross-posting ******* *** Please forward this message to other interested colleagues and community members *** The 11th Workshop on Detection and Classification of Acoustic Scenes and Events, *DCASE 2026, will be held in Boston on 28-29 October*. It is co-organized by Bose Corporation, MIT, and Tufts University. DCASE Workshop 2026 will be co-located with the *BioDCASE Workshop* <https://biodcase.github.io/workshop2026/> (October 23, online workshop), which focuses on Bio-acoustics, and the *SANE Workshop* <https://www.saneworkshop.org/sane2026/> (October 30 at MIT), which is a one-day event gathering researchers and students in speech and audio from the Northeast of the American continent. The SANE Workshop alternates between Boston and New York City every year. As in previous years, the workshop is organized in conjunction with the DCASE challenge <https://dcase.community/challenge2026/>. We aim to bring together researchers from many different universities, research organizations and companies with an interest in the topic, and provide the opportunity for scientific exchange of ideas and opinions. We invite submissions on the topics of computational analysis of acoustic scenes and sound events, including but not limited to: *Tasks in computational environmental audio analysis* - Environmental audio classification and tagging - Sound event detection and localization - Natural language based audio retrieval - Bio-acoustics - Audio captioning - Environmental audio generation - Anomalous sound detection - Audio source separation *Multimodal environmental audio analysis and generation* - Audio question answering - Audio-language models for acoustic reasoning and scene understanding - Large Audio Language Models (LALMs) for audio, acoustics, and scene grounding - Audio-visual spatial segmentation - Language-guided spatial and embodied audio understanding - Controllable natural language based audio generation - Perception-aligned evaluation of generative audio beyond FID/FAD - Video to audio generation - Multimodal LALM benchmarks - Multimodal representation learning and foundational models *Methods for computational environmental audio analysis* - Signal processing and auditory-motivated methods - Machine learning methods: e.g. feature learning, self-supervised learning, foundation modeling for environmental audio - Cross-disciplinary methods involving, e.g., acoustics, biology, psychology, geography, materials science, transports science - Generative modeling - Perceptual analysis and modeling of acoustic environments *Resources, applications, and evaluations of computational environmental-audio analysis* - Publicly available datasets: e.g., multichannel datasets, noisy datasets, missing datasets, mismatched device datasets - Publicly available software, taxonomies, and ontologies, evaluation procedures - Benchmark datasets for evaluation - Modeling, simulation, and synthesis of realistic acoustic scenes - Ethics, privacy, responsible research - Applications We strongly encourage reproducible research with open-source code and open data, though it is not mandatory. *Important notice for challenge participants:* Description of systems submitted to the DCASE2026 Challenge is expected to be expanded from the challenge technical report submissions to comply with the format of a scientific paper. This generally means describing the scientific novelty and including more discussions such as ablation studies for additional modules in your method. The paper submission portal is now open at: <https://dcase.community/workshop2025/submission> https://dcase.community/workshop2026/submission *Important Dates (midnight AoE)* - 05 Jul 2026, Workshop abstract submission deadline - 12 Jul 2026, Workshop final submission deadline - 06 Sep 2026, Notification of paper acceptance - 20 Sep 2026, Camera ready submission - 28 Oct 2026 - 29 Oct 2026, Workshop *DCASE 2026 Technical Program Chairs* Frederic Font, Universitat Pompeu Fabra Marko Stamenovic, Bose Corp. Bashima Islam, Worcester Polytechnic Institute Mark Cartwright, New Jersey Institute of Technology *DCASE 2026 General Chairs* Shuo Zhang, Bose Corp./Tufts University Anna Huang, Massachusetts Institute of Technology Paris Smaragdis, Massachusetts Institute of Technology If you have any questions, please contact Frederic Font at frederic.font@xxxxxxxx --000000000000d65213065375b397 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable <div dir=3D"ltr"><p style=3D"color:rgba(0,0,0,0.87);font-family:Roboto,Robo= toDraft,Helvetica,Arial,sans-serif;font-size:14px">******* Apologies for cr= oss-posting *******</p><p dir=3D"ltr" style=3D"line-height:1.38;margin-top:= 0pt;margin-bottom:0pt"><span style=3D"font-size:11pt;font-family:Arial,sans= -serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:n= ormal;font-variant-east-asian:normal;font-variant-alternates:normal;vertica= l-align:baseline">*** Please forward this message to other interested colle= agues and community members ***</span></p><p style=3D"color:rgba(0,0,0,0.87= );font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px"= >The 11th Workshop on Detection and Classification of Acoustic Scenes and E= vents,=C2=A0<b>DCASE 2026, will be held in Boston on 28-29 October</b>. It = is co-organized by Bose Corporation, MIT, and Tufts University.<br></p><p s= tyle=3D"color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Ari= al,sans-serif;font-size:14px">DCASE Workshop 2026 will be co-located with t= he<a href=3D"https://biodcase.github.io/workshop2026/" target=3D"_blank" re= l=3D"nofollow" style=3D"text-decoration:none;color:rgb(26,115,232)">=C2=A0<= b>BioDCASE Workshop</b></a>=C2=A0(October 23, online workshop), which focus= es on Bio-acoustics, and the<a href=3D"https://www.saneworkshop.org/sane202= 6/" target=3D"_blank" rel=3D"nofollow" style=3D"text-decoration:none;color:= rgb(26,115,232)">=C2=A0<b>SANE Workshop</b></a>=C2=A0(October 30 at MIT), w= hich is a one-day event gathering researchers and students in speech and au= dio from the Northeast of the American continent. The SANE Workshop alterna= tes between Boston and New York City every year.<br><br>As in previous year= s, the workshop is organized in conjunction with the=C2=A0<a href=3D"https:= //dcase.community/challenge2026/" target=3D"_blank" rel=3D"nofollow" style= =3D"text-decoration:none;color:rgb(26,115,232)">DCASE challenge</a>. We aim= to bring together researchers from many different universities, research o= rganizations and companies with an interest in the topic, and provide the o= pportunity for scientific exchange of ideas and opinions.<br><br>We invite = submissions on the topics of computational analysis of acoustic scenes and = sound events, including but not limited to:<br><br><b>Tasks in computationa= l environmental audio analysis</b><b></b></p><ul style=3D"color:rgba(0,0,0,= 0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:1= 4px"><li>Environmental audio classification and tagging</li><li>Sound event= detection and localization</li><li>Natural language based audio retrieval<= /li><li>Bio-acoustics</li><li>Audio captioning</li><li>Environmental audio = generation</li><li>Anomalous sound detection</li><li>Audio source separatio= n</li></ul><p style=3D"color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraf= t,Helvetica,Arial,sans-serif;font-size:14px"><b>Multimodal environmental au= dio analysis and generation</b><b></b></p><ul style=3D"color:rgba(0,0,0,0.8= 7);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px= "><li>Audio question answering</li><li>Audio-language models for acoustic r= easoning and scene understanding=C2=A0</li><li>Large Audio Language Models = (LALMs) for audio, acoustics, and scene grounding</li><li>Audio-visual spat= ial segmentation</li><li>Language-guided spatial and embodied audio underst= anding</li><li>Controllable natural language based audio generation</li><li= >Perception-aligned evaluation of generative audio beyond FID/FAD</li><li>V= ideo to audio generation</li><li>Multimodal LALM benchmarks=C2=A0</li><li>M= ultimodal representation learning and foundational models</li></ul><p style= =3D"color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,s= ans-serif;font-size:14px"><b>Methods for computational environmental audio = analysis</b><b></b></p><ul style=3D"color:rgba(0,0,0,0.87);font-family:Robo= to,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px"><li>Signal proces= sing and auditory-motivated methods</li><li>Machine learning methods: e.g. = feature learning, self-supervised learning, foundation modeling for environ= mental audio</li><li>Cross-disciplinary methods involving, e.g., acoustics,= biology, psychology, geography, materials science, transports science</li>= <li>Generative modeling</li><li>Perceptual analysis and modeling of acousti= c environments</li></ul><p style=3D"color:rgba(0,0,0,0.87);font-family:Robo= to,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px"><b>Resources, app= lications, and evaluations of computational environmental-audio analysis</b= ><b></b></p><ul style=3D"color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDr= aft,Helvetica,Arial,sans-serif;font-size:14px"><li>Publicly available datas= ets: e.g., multichannel datasets, noisy datasets, missing datasets, mismatc= hed device datasets</li><li>Publicly available software, taxonomies, and on= tologies, evaluation procedures</li><li>Benchmark datasets for evaluation</= li><li>Modeling, simulation, and synthesis of realistic acoustic scenes</li= ><li>Ethics, privacy, responsible research</li><li>Applications</li></ul><p= style=3D"color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,A= rial,sans-serif;font-size:14px">We strongly encourage reproducible research= with open-source code and open data, though it is not mandatory.</p><p sty= le=3D"color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial= ,sans-serif;font-size:14px"><b>Important notice for challenge participants:= </b>=C2=A0Description of systems submitted to the DCASE2026 Challenge is ex= pected to be expanded from the challenge technical report submissions to co= mply with the format of a scientific paper. This generally means describing= the scientific novelty and including more discussions such as ablation stu= dies for additional modules in your method.</p><p style=3D"color:rgba(0,0,0= ,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:= 14px">The paper submission portal is now open at:<a href=3D"https://dcase.c= ommunity/workshop2025/submission" target=3D"_blank" rel=3D"nofollow" style= =3D"text-decoration:none;color:rgb(26,115,232)">=C2=A0</a><a href=3D"https:= //dcase.community/workshop2026/submission" target=3D"_blank" rel=3D"nofollo= w" style=3D"text-decoration:none;color:rgb(26,115,232)">https://dcase.commu= nity/workshop2026/submission</a>=C2=A0</p><p style=3D"color:rgba(0,0,0,0.87= );font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px"= ><b>Important Dates (midnight AoE)</b><b></b></p><ul style=3D"color:rgba(0,= 0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-si= ze:14px"><li>05 Jul 2026, Workshop abstract submission deadline</li><li>12 = Jul 2026, Workshop final submission deadline</li><li>06 Sep 2026, Notificat= ion of paper acceptance</li><li>20 Sep 2026, Camera ready submission</li><l= i>28 Oct 2026 - 29 Oct 2026, Workshop</li></ul><p style=3D"color:rgba(0,0,0= ,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:= 14px"><b>DCASE 2026 Technical Program Chairs</b><b></b></p><p style=3D"colo= r:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-seri= f;font-size:14px">Frederic Font, Universitat Pompeu Fabra</p><p style=3D"co= lor:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-se= rif;font-size:14px">Marko Stamenovic, Bose Corp.</p><p style=3D"color:rgba(= 0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-= size:14px">Bashima Islam, Worcester Polytechnic Institute</p><p style=3D"co= lor:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-se= rif;font-size:14px">Mark Cartwright, New Jersey Institute of Technology=C2= =A0</p><p style=3D"color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,He= lvetica,Arial,sans-serif;font-size:14px"><br></p><p style=3D"color:rgba(0,0= ,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-siz= e:14px"><b>DCASE 2026 General Chairs</b><b></b></p><p style=3D"color:rgba(0= ,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-s= ize:14px">Shuo Zhang, Bose Corp./Tufts University</p><p style=3D"color:rgba= (0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font= -size:14px">Anna Huang, Massachusetts Institute of Technology</p><p dir=3D"= ltr" style=3D"color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helveti= ca,Arial,sans-serif;font-size:14px;line-height:1.2;text-align:justify;margi= n-top:0pt;margin-bottom:8pt"></p><p style=3D"color:rgba(0,0,0,0.87);font-fa= mily:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px">Paris Sm= aragdis, Massachusetts Institute of Technology</p><p dir=3D"ltr" style=3D"l= ine-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style=3D"font-size:= 11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transpa= rent;font-variant-numeric:normal;font-variant-east-asian:normal;font-varian= t-alternates:normal;vertical-align:baseline">If you have any questions, ple= ase contact Frederic Font at=C2=A0<span style=3D"color:inherit"><a aria-has= popup=3D"menu" href=3D"mailto:frederic.font@xxxxxxxx" rel=3D"noopener norefe= rrer nofollow" target=3D"_blank" style=3D"color:rgb(18,100,163);text-decora= tion:none">frederic.font@xxxxxxxx</a>.</span></span></p><div class=3D"gmail-= adL"><br></div><div class=3D"gmail-yj6qo" style=3D"scroll-behavior: auto;">= </div></div> --000000000000d65213065375b397--