Subject: [AUDITORY] [CfP] HSCMA 2024 (ICASSP 2024 Satellite Workshop) From: "Kim, Minje" <minje@xxxxxxxx> Date: Thu, 30 Nov 2023 17:32:24 +0000--_000_C7E8C38ADEA34F7BAD49A75D91609649indianaedu_ Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable (Apologies for cross-posting) Introduction The Workshop on Hands-free Speech Communication and Microphone Arrays (HSCM= A) invites contributions. Established in 2005, HSCMA has evolved into a piv= otal platform for sharing breakthrough ideas and solutions in hands-free sp= eech communication and microphone arrays. Recently, both speech and audio c= ommunities have faced challenges and opportunities in making powerful neura= l network models available for "efficient" on-device processing, while adap= ting to each individual user's "personal" speech traits (e.g., dialects and= non-nativeness) and acoustic environments, which are the two main themes o= f this year's workshop. In addition, the tradeoff between performance impro= vement and increased use of personal data becomes trickier, too, from the p= rivacy preservation perspective. The workshop will be a great opportunity t= o push the limits of speech processing systems in various hands-free applic= ation scenarios. HSCMA 2024 will be held as a satellite workshop of ICASSP 2024, which will = be held in Seoul, Korea (Apr. 14-19). There will be two keynote talks and a= panel discussion on privacy and efficiency issues of speech processing. In= addition, we call for paper contributions from the audio and speech resear= ch communities. The workshop is sponsored by the IEEE SPS Audio and Acousti= c Signal Processing Technical Committee, Speech and Language Processing Tec= hnical Committee, and Data Science Initiative. Keynote Speakers * Yi Luo, Tencent * Nancy F. Chen, A*STAR Panel Discussion on Privacy and Efficiency of Speech Processing * Berrak Sisman, University of Texas at Dallas * Athanasios Mouchitaris, Amazon Alexa * Bhiksha Raj, CMU LTI Topics of Interest * Hands-free speech communication * Microphone arrays * Speech recognition and synthesis * Voice conversion in noisy environments * Voice-controlled assistants and teleconferencing systems * Beamforming techniques, acoustic echo cancellation, source separation * Multi-modal speech processing and enhancement * Personalization and privacy preservation Important Dates * Submission Deadline: December 20, 2023 * Review Assignment: January 8, 2024 * Review Submission Deadline: January 22, 2024 * Author Notification: January 29, 2024 * Camera-Ready Submission Deadline: February 8, 2024 * Workshop Date: TBD (it will be either right before the main ICASSP te= chnical programs or after) Information for Authors This year, publications will be in a two-track structure: the archival and = non-archival tracks. * Archival Track: The archival track will accept novel paper contributi= ons, which will be published at IEEE Xplore. Please submit your paper using= this link<https://cmsworkshops.com/ICASSP2024/Papers/Submission.asp?Type= =3DWS&ID=3D15>. The papers must follow ICASSP 2024's formatting guideline<h= ttps://cmsworkshops.com/ICASSP2024/papers/paper_kit.php> (4 pages + 1 addit= ional page for references) to be published in IEEE Xplore. All submissions = will go through a peer-review process. * Non-Archival Track: We accept non-archival track papers, which will N= OT be published through IEEE Xplore, although we will still post them on ou= r website. The non-archival track accepts work-in-progress, already publish= ed works, or demonstrations of systems, for those who want to socialize the= research ideas with like-minded audiences. Please note that the papers sho= uld still be technically sound and follow ICASSP 2024's formatting guideli= ne<https://cmsworkshops.com/ICASSP2024/papers/paper_kit.php>, while we allo= w longer page limitations of up to 8 pages (plus one references-only page).= For this track, please submit the paper using this link<https://cmt3.resea= rch.microsoft.com/HSCMA2024>. Final Note The HSCMA 2024 is a unique opportunity to push the boundaries in hands-free= speech processing systems. We encourage interdisciplinary work and welcome= demonstrations of experimental systems and prototypes. Join us in shaping = the future of hands-free speech communication! For more details, visit HSCMA 2024 website<https://sites.google.com/view/hs= cma2024>. Sincerely, Minje Kim (minje@xxxxxxxx<mailto:minje@xxxxxxxx>) Paola Garcia (lgarci27@xxxxxxxx<mailto:lgarci27@xxxxxxxx>) Jonah Casebeer (jonah.casebeer@xxxxxxxx<mailto:jonah.casebeer@xxxxxxxx>) HSCMA 2024 Organizers --_000_C7E8C38ADEA34F7BAD49A75D91609649indianaedu_ Content-Type: text/html; charset="us-ascii" Content-ID: <39DEBB2D95B7024F8FCF06FE21F36C9A@xxxxxxxx> Content-Transfer-Encoding: quoted-printable <html> <head> <meta http-equiv=3D"Content-Type" content=3D"text/html; charset=3Dus-ascii"= > </head> <body style=3D"overflow-wrap: break-word; -webkit-nbsp-mode: space; line-br= eak: after-white-space;"> <div style=3D"caret-color: rgba(0, 0, 0, 0.87); color: rgba(0, 0, 0, 0.87);= "><font color=3D"#000000">(Apologies for cross-posting)</font></div> <div style=3D"caret-color: rgba(0, 0, 0, 0.87); color: rgba(0, 0, 0, 0.87);= "><b style=3D"font-size: 14px;"><font color=3D"#000000"><br> </font></b></div> <div style=3D"caret-color: rgba(0, 0, 0, 0.87); color: rgba(0, 0, 0, 0.87);= "><b style=3D"font-size: 14px;"><font color=3D"#000000">Introduction</font>= </b></div> <div style=3D"caret-color: rgba(0, 0, 0, 0.87); color: rgba(0, 0, 0, 0.87);= "> <div><font color=3D"#000000"><br> </font></div> <div><font color=3D"#000000">The Workshop on Hands-free Speech Communicatio= n and Microphone Arrays (HSCMA) invites contributions. Established in 2005,= HSCMA has evolved into a pivotal platform for sharing breakthrough ideas a= nd solutions in hands-free speech communication and microphone arrays. Recently, both speech and audio commu= nities have faced challenges and opportunities in making powerful neural ne= twork models available for "efficient" on-device processing, whil= e adapting to each individual user's "personal" speech traits (e.g., dialects and non-nativeness) and acoustic environment= s, which are the two main themes of this year's workshop. In addition, the = tradeoff between performance improvement and increased use of personal data= becomes trickier, too, from the privacy preservation perspective. The workshop will be a great opportunity= to push the limits of speech processing systems in various hands-free appl= ication scenarios.</font></div> <div><font color=3D"#000000"><br> </font></div> <div><font color=3D"#000000">HSCMA 2024 will be held as a satellite worksho= p of ICASSP 2024, which will be held in Seoul, Korea (Apr. 14-19). There wi= ll be two keynote talks and a panel discussion on privacy and efficiency is= sues of speech processing. In addition, we call for paper contributions from the audio and speech research communi= ties. The workshop is sponsored by the IEEE SPS Audio and Acoustic Signal P= rocessing Technical Committee, Speech and Language Processing Technical Com= mittee, and Data Science Initiative. </font></div> <div><font color=3D"#000000"><br> </font></div> <div style=3D"font-size: 14px;"><b><font color=3D"#000000">Keynote Speakers= </font></b></div> <div> <ul> <li><font color=3D"#000000">Yi Luo, Tencent</font></li><li><font color=3D"#= 000000">Nancy F. Chen, A*STAR</font></li></ul> </div> <div><font color=3D"#000000"><br> </font></div> <div style=3D"font-size: 14px;"><b><font color=3D"#000000">Panel Discussion= on Privacy and Efficiency of Speech Processing</font></b></div> <div> <ul> <li><font color=3D"#000000">Berrak Sisman, University of Texas at Dallas</f= ont></li><li><font color=3D"#000000">Athanasios Mouchitaris, Amazon Alexa</= font></li><li><font color=3D"#000000">Bhiksha Raj, CMU LTI</font></li></ul> <div><font color=3D"#000000"><br> </font></div> </div> <div> <div style=3D"font-size: 14px;"><b><font color=3D"#000000">Topics of Intere= st</font></b></div> <div> <ul> <li><font color=3D"#000000">Hands-free speech communication</font></li><li>= <font color=3D"#000000">Microphone arrays</font></li><li><font color=3D"#00= 0000">Speech recognition and synthesis</font></li><li><font color=3D"#00000= 0">Voice conversion in noisy environments</font></li><li><font color=3D"#00= 0000">Voice-controlled assistants and teleconferencing systems</font></li><= li><font color=3D"#000000">Beamforming techniques, acoustic echo cancellati= on, source separation</font></li><li><font color=3D"#000000">Multi-modal sp= eech processing and enhancement</font></li><li><font color=3D"#000000">Pers= onalization and privacy preservation</font></li></ul> </div> </div> <div><font color=3D"#000000"><br> </font></div> <div style=3D"font-size: 14px;"><b><font color=3D"#000000">Important Dates<= /font></b></div> <div> <ul> <li><font color=3D"#000000">Submission Deadline: December 20, 2023</font></= li><li><font color=3D"#000000">Review Assignment: January 8, 2024</font></l= i><li><font color=3D"#000000">Review Submission Deadline: January 22, 2024<= /font></li><li><font color=3D"#000000">Author Notification: January 29, 202= 4</font></li><li><font color=3D"#000000">Camera-Ready Submission Deadline: = February 8, 2024</font></li><li><font color=3D"#000000">Workshop Date: TBD = (it will be either right before the main ICASSP technical programs or after= )</font></li></ul> </div> <div><font color=3D"#000000"><br> </font></div> <div style=3D"font-size: 14px;"><b><font color=3D"#000000">Information for = Authors</font></b></div> <div><font color=3D"#000000">This year, publications will be in a two-track= structure: the archival and non-archival tracks. </font></div> <div> <ul> <li><font color=3D"#000000">Archival Track: The archival track will accept = novel paper contributions, which will be published at IEEE Xplore. Please s= ubmit your paper using <a href=3D"https://cmsworkshops.com/ICASSP2024/= Papers/Submission.asp?Type=3DWS&ID=3D15" target=3D"_blank" rel=3D"nofol= low" data-saferedirecturl=3D"https://www.google.com/url?hl=3Den&q=3Dhtt= ps://cmsworkshops.com/ICASSP2024/Papers/Submission.asp?Type%3DWS%26ID%3D15&= amp;source=3Dgmail&ust=3D1701451748033000&usg=3DAOvVaw2ioaQN5HE4eL-= c98DNmaCd" style=3D"text-decoration: none; color: rgb(26, 115, 232);">this link</a>. The papers must follow <a href=3D"https://cmsworkshops.com/= ICASSP2024/papers/paper_kit.php" target=3D"_blank" rel=3D"nofollow" data-sa= feredirecturl=3D"https://www.google.com/url?hl=3Den&q=3Dhttps://cmswork= shops.com/ICASSP2024/papers/paper_kit.php&source=3Dgmail&ust=3D1701= 451748034000&usg=3DAOvVaw241nKDWrxRnwf3rpuDFT_v" style=3D"text-decorati= on: none; color: rgb(26, 115, 232);">ICASSP 2024's formatting guideline</a> (4 pages + 1 additional page for refe= rences) to be published in IEEE Xplore. All submissions will go through a p= eer-review process. </font></li><li><font color=3D"#000000">Non-Archiv= al Track: We accept non-archival track papers, which will NOT be published = through IEEE Xplore, although we will still post them on our website. The n= on-archival track accepts work-in-progress, already published works, or demonstrations of systems, for those who want to socialize the research id= eas with like-minded audiences. Please note that the papers should still be= technically sound and follow <a href=3D"https://cmsworkshops.co= m/ICASSP2024/papers/paper_kit.php" target=3D"_blank" rel=3D"nofollow" data-= saferedirecturl=3D"https://www.google.com/url?hl=3Den&q=3Dhttps://cmswo= rkshops.com/ICASSP2024/papers/paper_kit.php&source=3Dgmail&ust=3D17= 01451748034000&usg=3DAOvVaw241nKDWrxRnwf3rpuDFT_v" style=3D"text-decora= tion: none; color: rgb(26, 115, 232);">ICASSP 2024's formatting guideline</a>, while we allow longer page limitations of= up to 8 pages (plus one references-only page). For this track, please subm= it the paper using<a href=3D"https://cmt3.research.microsoft.com/HSCMA2024"= target=3D"_blank" rel=3D"nofollow" data-saferedirecturl=3D"https://www.goo= gle.com/url?hl=3Den&q=3Dhttps://cmt3.research.microsoft.com/HSCMA2024&a= mp;source=3Dgmail&ust=3D1701451748034000&usg=3DAOvVaw3SuEwMS_bdxDvs= 7yV1Sk9q" style=3D"text-decoration: none; color: rgb(26, 115, 232);"> = this link</a>. </font></li></ul> </div> <div><font color=3D"#000000"><br> </font></div> <div style=3D"font-size: 14px;"><b><font color=3D"#000000">Final Note</font= ></b></div> <div><font color=3D"#000000">The HSCMA 2024 is a unique opportunity to push= the boundaries in hands-free speech processing systems. We encourage inter= disciplinary work and welcome demonstrations of experimental systems and pr= ototypes. Join us in shaping the future of hands-free speech communication!</font></div> <div><font color=3D"#000000"><br> </font></div> <div><font color=3D"#000000">For more details, visit <a href=3D"https:= //sites.google.com/view/hscma2024" target=3D"_blank" rel=3D"nofollow" data-= saferedirecturl=3D"https://www.google.com/url?hl=3Den&q=3Dhttps://sites= .google.com/view/hscma2024&source=3Dgmail&ust=3D1701451748034000&am= p;usg=3DAOvVaw2eskkLdwxck-PBQlsJFBqT" style=3D"text-decoration: none; color= : rgb(26, 115, 232);">HSCMA 2024 website</a>.</font></div> </div> <div style=3D"caret-color: rgba(0, 0, 0, 0.87); color: rgba(0, 0, 0, 0.87);= "><font color=3D"#000000"><br> </font></div> <div style=3D"caret-color: rgba(0, 0, 0, 0.87); color: rgba(0, 0, 0, 0.87);= "><font color=3D"#000000">Sincerely,</font></div> <div style=3D"caret-color: rgba(0, 0, 0, 0.87); color: rgba(0, 0, 0, 0.87);= "><font color=3D"#000000">Minje Kim (<a href=3D"mailto:minje@xxxxxxxx" t= arget=3D"_blank" rel=3D"nofollow" style=3D"text-decoration: none; color: rg= b(26, 115, 232);">minje@xxxxxxxx</a>)</font></div> <div style=3D"caret-color: rgba(0, 0, 0, 0.87); color: rgba(0, 0, 0, 0.87);= "><font color=3D"#000000">Paola Garcia (</font><a href=3D"mailto:lgarci27@xxxxxxxx= hu.edu" target=3D"_blank" rel=3D"nofollow" style=3D"text-decoration: none; = color: rgb(26, 115, 232);">lgarci27@xxxxxxxx</a>)</div> <div style=3D"caret-color: rgba(0, 0, 0, 0.87); color: rgba(0, 0, 0, 0.87);= "><font color=3D"#000000">Jonah Casebeer (</font><span style=3D"font-family= : Roboto, RobotoDraft, Helvetica, Arial, sans-serif;"><a href=3D"mailto:jon= ah.casebeer@xxxxxxxx" target=3D"_blank" rel=3D"nofollow" style=3D"text-deco= ration: none; color: rgb(26, 115, 232);">jonah.casebeer@xxxxxxxx</a>)</span= ></div> <div style=3D"caret-color: rgba(0, 0, 0, 0.87); color: rgba(0, 0, 0, 0.87);= "><font color=3D"#000000">HSCMA 2024 Organizers</font></div> </body> </html> --_000_C7E8C38ADEA34F7BAD49A75D91609649indianaedu_--