Registration reminder: CHiME 2013, 2nd International Workshop on Machine Listening in Multisource Environments (jon )


Subject: Registration reminder: CHiME 2013, 2nd International Workshop on Machine Listening in Multisource Environments
From:    jon  <j.barker@xxxxxxxx>
Date:    Tue, 9 Apr 2013 14:34:21 +0100
List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>

--Apple-Mail=_128C9FA6-FB70-4CBA-A8DC-3CD402BFBFB3 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=iso-8859-1 ---------------------------------------------- 2nd International Workshop on Machine Listening in Multisource Environments (CHiME 2013) in conjunction with ICASSP 2013 June 1, 2013, Vancouver, Canada http://spandh.dcs.shef.ac.uk/chime_workshop/ ---------------------------------------------- *NEW REGISTRATION DEADLINE*: May 11, 2013 *FINAL PROGRAMME* http://spandh.dcs.shef.ac.uk/chime_workshop/programme.html *KEYNOTES* Model-based Speech Separation and Recognition: Yesterday, Today, and=20 Tomorrow Steven J. Rennie, IBM Recently, model-based approaches for multi-talker speech separation and=20= recognition have demonstrated great success in highly constrained=20 scenarios, and efficient algorithms for separating data with literally=20= *trillions* of underlying states have been unveiled. In less constrained=20= scenarios, deep neural networks (DNNs) learned on features inspired by=20= human auditory processing have shown great capacity for directly=20 learning masking functions from parallel data. Ideally, a robust speech=20= separation/recognition system should be continuously learning, adapting,=20= and exploiting structure that is present in both target and peripheral=20= signals and interactions, make minimal assumptions about the data to be=20= separated/recognized, not require parallel data streams, and have=20 essentially unlimited information capacity. In this talk I will briefly=20= review the current state of robust speech separation/recognition=20 technology--where we are, where we apparently need to go, and how we=20 might get there. I=92 will then discuss in more detail recent work that = I=92 have=20 been involved with that is aligned with these goals. Specifically, I=20 will discuss some new results on efficiently learning the structure of=20= models and efficiently optimizing a wide class of matrix-valued=20 functions, some recent work on Factorial Restricted Boltzmann machines=20= for robust ASR, and finally, Direct product DBNs, a new architecture=20 that makes it feasible to learn DNNs with literally *millions* of = neurons. Recognizing and Classifying Environmental Sounds Daniel P.W. Ellis, Columbia University Animal hearing exists to extract useful information out of the=20 environment, and for a lot of animals for a large portion of the=20 evolutionary history of hearing this sound environment has not consisted=20= of speech or music, but of more generic acoustic information arising=20 from collisions, motions, and other events in the external world. This=20= aspect of sound analysis -- getting information out of non-speech,=20 non-music, environmental sounds -- is finally beginning to gain=20 popularity in research since it holds promise as a tool for automatic=20 search and retrieval of audio/video recordings, an increasingly urgent=20= problem. I will discuss our recent work in using audio analysis to=20 manage and search environmental sound archives (including personal audio=20= lifelogs and consumer video collections), and illustrate with some of=20 the approaches that work more or less well, with an effort to explain = why. *OVERVIEW* CHiME 2013 will consider the challenge of developing machine listening=20= applications for operation in multisource environments, i.e. real-world=20= conditions with acoustic clutter, where the number and nature of the=20 sound sources is unknown and changing over time. It will bring together=20= researchers from a broad range of disciplines (computational hearing,=20 blind source separation, speech recognition, machine learning) to=20 discuss novel and established approaches to this problem. The=20 cross-fertilisation of ideas will foster fresh approaches that=20 efficiently combine the complementary strengths of each research field. One highlight of the Workshop will be the presentation of the results of=20= the 2nd CHiME Speech Separation and Recognition Challenge, that is a=20 two-microphone multisource speech separation and recognition challenge=20= supported by the IEEE AASP, MLSP and SLTC Technical Committees. To find=20= out more, please visit http://spandh.dcs.shef.ac.uk/chime_challenge. *REGISTRATION* To register, please visit http://spandh.dcs.shef.ac.uk/chime_workshop/registration.html The registration fee is 35 UK pounds and includes admission to the=20 sessions, electronic proceedings, buffet lunch, and tee and coffee = breaks. *VENUE* The workshop is taking place at the Hyatt Regency Vancouver, 655 Burrard=20= Street -- close to the ICASSP 2013 venue -- on the day after ICASSP=20 finishes, Saturday 1st June. Information about accommodation and how to=20= get to and from downtown Vancouver can be found on the main ICASSP = website: http://www.icassp2013.com See you in Vancouver. Best regards, CHiME Organising Committee --=20 Dr. Jon Barker, Department of Computer Science, University of Sheffield, Sheffield, S1 4DP, UK Phone: +44-(0)114-22 21824 FAX: +44-(0)114-222 1810 Email: j.barker@xxxxxxxx http://www.dcs.shef.ac.uk/~jon --Apple-Mail=_128C9FA6-FB70-4CBA-A8DC-3CD402BFBFB3 Content-Transfer-Encoding: quoted-printable Content-Type: text/html; charset=iso-8859-1 <html><head><meta http-equiv=3D"Content-Type" content=3D"text/html = charset=3Diso-8859-1"></head><body style=3D"word-wrap: break-word; = -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; = "><div>&nbsp; &nbsp; &nbsp; = &nbsp;----------------------------------------------</div><div>&nbsp; = &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;2nd International = Workshop on</div><div>Machine Listening in Multisource Environments = (CHiME 2013)</div><div><br></div><div>&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; = &nbsp; &nbsp; in conjunction with ICASSP 2013</div><div>&nbsp; &nbsp; = &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; June 1, 2013, Vancouver, = Canada</div><div><br></div><div>&nbsp; &nbsp; &nbsp; &nbsp; <a = href=3D"http://spandh.dcs.shef.ac.uk/chime_workshop/">http://spandh.dcs.sh= ef.ac.uk/chime_workshop/</a></div><div>&nbsp; &nbsp; &nbsp; = &nbsp;----------------------------------------------</div><div><br></div><= div><br></div><div>*NEW REGISTRATION DEADLINE*: May 11, = 2013</div><div><br></div><div><br></div><div>*FINAL = PROGRAMME*</div><div><br></div><div><a = href=3D"http://spandh.dcs.shef.ac.uk/chime_workshop/programme.html">http:/= /spandh.dcs.shef.ac.uk/chime_workshop/programme.html</a></div><div><br></d= iv><div><br></div><div>*KEYNOTES*</div><div><br></div><div>Model-based = Speech Separation and Recognition: Yesterday, Today, = and&nbsp;</div><div>Tomorrow</div><div>Steven J. Rennie, = IBM</div><div><br></div><div>Recently, model-based approaches for = multi-talker speech separation and&nbsp;</div><div>recognition have = demonstrated great success in highly = constrained&nbsp;</div><div>scenarios, and efficient algorithms for = separating data with literally&nbsp;</div><div>*trillions* of underlying = states have been unveiled. In less = constrained&nbsp;</div><div>scenarios, deep neural networks (DNNs) = learned on features inspired by&nbsp;</div><div>human auditory = processing have shown great capacity for = directly&nbsp;</div><div>learning masking functions from parallel data. = Ideally, a robust speech&nbsp;</div><div>separation/recognition system = should be continuously learning, adapting,&nbsp;</div><div>and = exploiting structure that is present in both target and = peripheral&nbsp;</div><div>signals and interactions, make minimal = assumptions about the data to be&nbsp;</div><div>separated/recognized, = not require parallel data streams, and have&nbsp;</div><div>essentially = unlimited information capacity. In this talk I will = briefly&nbsp;</div><div>review the current state of robust speech = separation/recognition&nbsp;</div><div>technology--where we are, where = we apparently need to go, and how we&nbsp;</div><div>might get there. I=92= will then discuss in more detail recent work that I=92 = have&nbsp;</div><div>been involved with that is aligned with these = goals. Specifically, I&nbsp;</div><div>will discuss some new results on = efficiently learning the structure of&nbsp;</div><div>models and = efficiently optimizing a wide class of = matrix-valued&nbsp;</div><div>functions, some recent work on Factorial = Restricted Boltzmann machines&nbsp;</div><div>for robust ASR, and = finally, Direct product DBNs, a new architecture&nbsp;</div><div>that = makes it feasible to learn DNNs with literally *millions* of = neurons.</div><div><br></div><div>Recognizing and Classifying = Environmental Sounds</div><div>Daniel P.W. Ellis, Columbia = University</div><div><br></div><div>Animal hearing exists to extract = useful information out of the&nbsp;</div><div>environment, and for a lot = of animals for a large portion of the&nbsp;</div><div>evolutionary = history of hearing this sound environment has not = consisted&nbsp;</div><div>of speech or music, but of more generic = acoustic information arising&nbsp;</div><div>from collisions, motions, = and other events in the external world. = &nbsp;This&nbsp;</div><div>aspect of sound analysis -- getting = information out of non-speech,&nbsp;</div><div>non-music, environmental = sounds -- is finally beginning to gain&nbsp;</div><div>popularity in = research since it holds promise as a tool for = automatic&nbsp;</div><div>search and retrieval of audio/video = recordings, an increasingly urgent&nbsp;</div><div>problem. &nbsp;I will = discuss our recent work in using audio analysis = to&nbsp;</div><div>manage and search environmental sound archives = (including personal audio&nbsp;</div><div>lifelogs and consumer video = collections), and illustrate with some of&nbsp;</div><div>the approaches = that work more or less well, with an effort to explain = why.</div><div><br></div><div><br></div><div>*OVERVIEW*</div><div><br></di= v><div>CHiME 2013 will consider the challenge of developing machine = listening&nbsp;</div><div>applications for operation in multisource = environments, i.e. real-world&nbsp;</div><div>conditions with acoustic = clutter, where the number and nature of the&nbsp;</div><div>sound = sources is unknown and changing over time. It will bring = together&nbsp;</div><div>researchers from a broad range of disciplines = (computational hearing,&nbsp;</div><div>blind source separation, speech = recognition, machine learning) to&nbsp;</div><div>discuss novel and = established approaches to this problem. = The&nbsp;</div><div>cross-fertilisation of ideas will foster fresh = approaches that&nbsp;</div><div>efficiently combine the complementary = strengths of each research field.</div><div><br></div><div>One highlight = of the Workshop will be the presentation of the results = of&nbsp;</div><div>the 2nd CHiME Speech Separation and Recognition = Challenge, that is a&nbsp;</div><div>two-microphone multisource speech = separation and recognition challenge&nbsp;</div><div>supported by the = IEEE AASP, MLSP and SLTC Technical Committees. To = find&nbsp;</div><div>out more, please visit <a = href=3D"http://spandh.dcs.shef.ac.uk/chime_challenge">http://spandh.dcs.sh= ef.ac.uk/chime_challenge</a>.</div><div><br></div><div><br></div><div>*REG= ISTRATION*</div><div><br></div><div>To register, please = visit</div><div><a = href=3D"http://spandh.dcs.shef.ac.uk/chime_workshop/registration.html">htt= p://spandh.dcs.shef.ac.uk/chime_workshop/registration.html</a></div><div><= br></div><div>The registration fee is 35 UK pounds and includes = admission to the&nbsp;</div><div>sessions, electronic proceedings, = buffet lunch, and tee and coffee = breaks.</div><div><br></div><div><br></div><div>*VENUE*</div><div><br></di= v><div>The workshop is taking place at the Hyatt Regency Vancouver, 655 = Burrard&nbsp;</div><div>Street -- close to the ICASSP 2013 venue -- on = the day after ICASSP&nbsp;</div><div>finishes, Saturday 1st June. = Information about accommodation and how to&nbsp;</div><div>get to and = from downtown Vancouver can be found on the main ICASSP = website:</div><div><a = href=3D"http://www.icassp2013.com">http://www.icassp2013.com</a></div><div= ><br></div><div><br></div><div>See you in = Vancouver.</div><div><br></div><div>Best = regards,</div><div><br></div><div>CHiME Organising = Committee</div><div><br></div><div apple-content-edited=3D"true"> <span class=3D"Apple-style-span" style=3D"border-collapse: separate; = border-spacing: 0px; "><span class=3D"Apple-style-span" = style=3D"border-collapse: separate; color: rgb(0, 0, 0); font-family: = Helvetica; font-size: medium; font-style: normal; font-variant: normal; = font-weight: normal; letter-spacing: normal; line-height: normal; = orphans: 2; text-indent: 0px; text-transform: none; white-space: normal; = widows: 2; word-spacing: 0px; -webkit-border-horizontal-spacing: 0px; = -webkit-border-vertical-spacing: 0px; = -webkit-text-decorations-in-effect: none; -webkit-text-size-adjust: = auto; -webkit-text-stroke-width: 0px; "><div style=3D"word-wrap: = break-word; -webkit-nbsp-mode: space; -webkit-line-break: = after-white-space; ">--&nbsp;<br>Dr. Jon Barker, Department of Computer = Science,<br>University of Sheffield, Sheffield, &nbsp;S1 4DP, = UK<br>Phone: +44-(0)114-22 21824 FAX: +44-(0)114-222 1810<br>Email: <a = href=3D"mailto:j.barker@xxxxxxxx">j.barker@xxxxxxxx</a> = &nbsp;<a = href=3D"http://www.dcs.shef.ac.uk/~jon">http://www.dcs.shef.ac.uk/~jon</a>= <br></div></span></span> </div> <br></body></html>= --Apple-Mail=_128C9FA6-FB70-4CBA-A8DC-3CD402BFBFB3--


This message came from the mail archive
/var/www/postings/2013/
maintained by:
DAn Ellis <dpwe@ee.columbia.edu>
Electrical Engineering Dept., Columbia University