ICML 2013国际会议论文集论文

所需积分/C币:10 2014-11-11 09:05:20 33.76MB PDF
12
收藏 收藏
举报

ICML 2013国际会议论文集论文,机器学习,深度学习领域,比较热
D小 Email list of participants Arik Kershenbaum arik nimbios. org Chris clark: cwc@ cornell. edu Christian Mason cason@g hmc. edu Dan Stowell dan. stowell @eecs qmuL ac uk Daniel sheldon sheldon @cs. umass. edu Davidledbetterledbetdr@gmail.com Emily hockman ehockman @utk. edu Faicel chamroukhi chamroukhiquniv-tIn. fr Florencia Noriega flo@nld. ds. mpg. de ForrestBriggsfbriggs@gmail.com Gianni Pavan gianni pavan @unipv. it Guangzhi qu gqu @oakland. edu Harold mills harold. mills gmail com Herve Glotin: glotin@ univ-lInr Ilyas Potamitis potamitis @staff. teicrete, gr Ishanu Chattopadhyay ishanu chattopadhyay @cornell. cdu Jean-Marc Prevot: jean-marc prevot @univ-tIn fr JelfKnewstubbjellk759@gmail.com Jerome sueur: sueur(@mnhn. fr Marian Popescu cp478@ cornell.edu Marie Trone mtrone@ valenciacollege edu Proc. of the 1st Workshop on machine Learning for bioacoustics glotin et al. Ed, 2013 Mike izbicki mike izbicki me Mohammad pourhomayoun mpourhoma gmail com Nicole bender nicole bender a marist. edu PeterDuganpeterdugan68@gmail.com Peter Dugan: pjd78@cornell. edu Sarah Hallerberg shallerberg @nld. ds. mpg. de Scottdobsondobsons13ahotmail.com Sebastian Huebner info@ sejona de Sebastien Paris sebastien.paris @lsis. org Steven ness snessasness net Sunil shahi sunil. shahi@ selu. edu WinfriedSegretierWiffried.Segretier@gmail.com Xanadu halkias xanadu halkias(@univ-tInfr Yann Lecun yann @cs. nyu. edu Yu Shiu ys587@ cornell. edu Yuan Hao yhao @cs. ucr.edu Ziang Xie zxie@berkeley. edu Proc. of the 1st Workshop on machine Learning for bioacoustics glotin et al. Ed, 2013 Contents Workshop at a glance page 4 Contributions page 4 Videos of presentations page 4 Abstract page 6 Objectives page 8 Invited talks overview page 2.Organization committee page 14 Organizers short CV page 14 3. Challenges page 17 Overview page I Bird challenge 20 Whale challenge p age 25 4 Schedule age 30 5. Proceedings page 32 32 Short papers Bird Challenge worknotes page 82 Proc. of the 1st Workshop on machine Learning for bioacoustics glotin et al. Ed, 2013 I Workshop at a glance 1. 1. Contributions Invited talks Prof. Christopher Clark, W-Cornell University, NY, USA Prof D. Sheldon and T G. Dietterich-Oregon State University, USA Prof, herve glotin-USTV Inst Univ de france. CNRs LSIS FR Dr Xanadu halkias -CNrS lsiS and UStV.Fr Prof. Y. Bengio- Department of Computer Science and Operations Research Canada research Chair in Statistical Learning algorithms Prof Diana reiss- Hunter College- CUNY. NYUSA Prof. Gianni payan pavia - Italy Prof Ofer Tchernichovski- Hunter College-CUNY. NY USA Dr Peter J. Dugan-Cornell University, NY, USA Full papers Rami abousleiman-Oakland University, Department of Electrical and Computer Engineering, Rochester, MI, USA Guangzhi Qu-Oakland University, Department of Computer Science and Engineering, Rochester, MI, USA Osamah Rawashdeh -Oakland University, Department of Electrical and Computer Engineering, Rochester, MI, USA Steven Ness-Department of Computer Science, University of Victoria, Canada Helena Symonds -OrcaLab, P.O. Box 510 Alert Bay, BC, Canada Paul Spong -OrcaLab P.O. Box 510 Alert Bay, BC, Canada George Tzanetakis-Department of Computer Science, University of Victoria, Canada Sebastien PARis-dyNi team LSIS CNRS UMR 7296 Aix-Marseille Universit Yann doh-dyni team LSIS CNRS UMR 7296 Universite Sud Toulon -Var Herve glotin-DYNi team LSIS CNRS UMR 7296 Universite Sud Toulon -var Xanadu halKias-DYNi team. LSIS CNRS UMR 7296 Universite Sud Toulon-Van Joseph razik -DYNI teaIn, LSIS CNRS UMR 7296, Universite Sud Toulon-Var Marian Popescu-Bioacoustics Research Program(BRP), Cornell University, Ithaca, NY, USA, 14850 Peter J. Dugan-Bioacoustics Research Program(BRP), Cornell University, Ithaca, NY, USA, 14850 Mohammad Pourhomayoun-Bioacoustics Research Program(BRP), Cornell University, Ithaca, NY, USA, 14850 Denise Risch-Northeast Fisheries Science Center. Woods hole. MA, USA, 0254 Sity, Ithaca. Harold w. Lewis Ill-Department of Systems Science and Industrial Engineering, Binghamton University, NY, USA, 13850 Christopher w. Clark-Bioacoustics Research Program(BRP), Cornell University, Ithaca, NY, USA, 14850 Mohammad Pourhomayoun- Bioacoustics Research Program(BRP), Cornell University, Ithaca, NY, USA, 14850 Peter Dugan-Bioacoustics Research Program(BRP), Cornell University, Ithaca, NY, USA, 14850 Marian Popescu -Bioacoustics Research Program(BRP), Cornell University, Ithaca, NY,USA,148.50 Denise risch -northeast fisheries science center woods hole MA usa. 02543 Harold w Lewis II-Department of Systems Science and Industrial Engineering, Binghamton University, NY, USA 13850 Christopher w. Clark-Bioacoustics Research Program(BRP), Cornell University, Ithaca, NY, USA, 148.50 Mohammad Pourhomayoun-Bioacoustics Research Program(BRP), Cornell University, Ithaca, NY, USA,148.50 Peter J. Dugan-Bioacoustics Research Program(BRP), Cornell University, Ithaca, NY, USA, 14850 Marian Popescu- Bioacoustics Research Program(BRP), Cornell University, Ithaca, NY, USA, 14850 Christopher W. Clark- Bioacoustics Research Program (BRP), Cornell University, Ithaca, NY, USA, 14850 Erick Stattner-LAMIA Lab University of the French West Indies and Guiana, france wilfried Segretier- LAMIA Lab. University of the French West Indies and Guiana, franc Martine Collard -LAMIA Lab. University of the French West Indies and Guiana, France Philippe Hunel-LAMIA Lab University of the French West Indies and Guiana, france Nicolas Vidot-LAMIA Lab. University of the French West Indies and Guiana, france Short papers Ales mishChenKo-satt sud-est/dYNi team, LSIS CNRS UMR 7296 Universite Sud Toulon-Var Herve glotin-DYNi team LSIS CNRS UMR 7296 Universite Sud Toulon -Var Evgeny Smirnov -Saint-Petersburg State University, Universitetskii prospekt 35, Petergof. Saint-Petersburg, Russia Proc. of the 1st Workshop on machine Learning for bioacoustics glotin et al. Ed, 2013 4 Bird Challenge worknotes Emmanouil Benetos-Department of Computer Science, City University London, London, UK Forrest Briggs -Oregon State University, Corvallis, OR, 97333, USA Olivier Dufour- LSIS Universite du Sud Toulon var Thierry Artieres-LIP6, Universite Paris 6 Herve glotin-Universite de Toulon CNRS LSIS. UMR 7296. 83957 La Garde. france Pascale giraudet- Universie du sud toulon van Dan Stowell and Mark D. Plumbley-Centre for Digital Music, Queen Mary, University of london Rafael hernandez murcia-Carlos Ill University of madrid, spain Victor Suarez Paniagua -Carlos Ill University of Madrid, Spain Jennifer G. Turner, Charles J. Turner-Academic Technology Services, UC Davis, Davis CA95616 USA 1. 2. Videos of presentations 06/20/2013 morning Ihttp://youtu.be/tdnmxgjDbj0:C.ClarkAdvancedHigh-performance-computingforMapping Marine mammals overs ecologically meaningful scales 2http://youtu.be/ubce2iLmmzy:O.Tchernichovski"physiologicalbrainprocessesthatunderlie song learning 3http:/youtu.be/u4wuobubh-w:Y.BengioDeepLearning:LookingForward 4http://youtu.be/9tf4uju-jnw:X.haLkiasClassificationofMysticeteExtracting spectrotemporal structures using Sparse Architectures 06/20/2013 afternoon: Ihttp://youtu.be_/vbDbWcsfss:H.Glotinsparsecodingfordeformedmarineorterrestrian events/Bird or Whale Cocktail Party 3D Tracking 2 hlp: //youlu. be/JPXEXcR634Q: Segretier el al. Song-based Classilication lechniques for Endangered Bird conservation 3http://youtu.be/pjmucnqmmwQ:D.Sheldonetal.maChineLearningandEcology 4http:/youtu.be/pbivo_7avng:Briggsetal.MultiLabelClassifchainsforBirdSound 5http:/youtu.be/yelOrwhYmo:G.PavanMonitoringbioacousticdiversityforresearch conservation and education 06/21/2013 morning: 1http://youtu.be/2-rwakr3bwq:P.DuganPraticalconsiderationsforhighperformanceon continuous passive acoustic data 2http://youtu.be/obuvibAomfu:Pourhomayounetal.huManScoringjointtoannforclassif 3http://youtu.be/xg3bdxg-nyw:G.Pavan'challengesinmonitoringindexingbioacoustic diversity 4http:/youtu.be/GWeR-ZBWOzw:Pourhomayounelal.'Classilicationoncontinuousregion 5http://youtu.be/m5itOlv303q:Popescuetal.PulseClassification 06/212013 afternoon http:/youtu.be/rtpneFi9nie:Parisetal.SparseCodingforwhalelocalization 2http:/youtu.beCzujc7vpq0:abOusleimanetal.'whAleClassification 3http:/youtu.be/lztsohmgm-m:Nessetal.orCaBigData 4http:/youtu.be/qo5negdfodi:ChallengeResultsHervegLotin Slidesofpresentationsarcavailablcathttp:/sabiod.univ-tin.fr Proc. of the 1st Workshop on machine Learning for bioacoustics glotin et al. Ed, 2013 1.2. Workshop abstract Biodiversity assessment remains one of the most difficult challenges encountered by ecologists and conservation biologists There is a critical need to describe and quantify the spatio-temporal dynamics of biodiversity over ecologically meaningful scales and to provide timely syntheses and interpretations so as to enable responsible decisions that rcducc risks to endangered spccics, populations and habitats from anthropogenic activitics This task has become even more urgent with the current increase of habitat loss and global environmental changes as a result of global commercial and industrial activities. The field of animal bioacoustics has received increasing attention due to its diverse potential benelits to science and society, and is increasingly required by regulatory agencies as a tool for timely monitoring and mitigation of environmental impacts from human activities. The increased expectations from bioacoustic research have been coincident with a dramatic increase in the spatial temporal and spectral scales of acoustic data collection efforts. The bottleneck at this point is not access to raw data. It is the inability to efficiently process visualize and interpret large volumes of data within an advanced, data management system This workshop brings together a cohort of world class scientists with expertise in animal bioacoustics, digital signal proccssing and machinc learning to specifically address the emerging field of bioacoustic machine learning, from basic to applied research The features and biological significance of animal sounds, while constrained by the physics of sound production and propagation, have evolved through the processes of natural selection. Additional insights have been gained through analysis and attempts of modeling of animal sounds as related to critical life functions(e.g. communicating, mating, migrating navigating, etc. ) social context; and individual, species and population identification. Most recently, researchers in the field have been exploring and identifying possible links and correlations between the dynamics of animal sound development and the evolution of human speech. These observations have led to both quantitative and qualitative advancements such as using Mris for monitoring bird song ontogeny and human brain activity associated with linguistic metaphors, or the usc of genctic algorithms to identify a possible common framework in the evolution of human and non-human cultural relationships. From an applied perspective, very basic, semi-automated systems for near- real-time acoustic detection of species of concern are being used by regulatory agencies to dynamically monitor and mitigate human activities, and there is increasing demand for such near-real-time capabilities Although, the majority of thc cxisting applications lend thcmsclvcs to widcly uscd advanced acoustic signal processing methodologies, the field has yet to successfully integrate robust signal processing and machine learning algorithms due to multiple and diverse challenges. Specifically, the dynamic and variable factors in the collection and anal ysis of raw data from both wild and captive environments often require the use of real- time or near-real-time systems that minimize manual interaction/supervision. This requirement can be strongly coupled with the creation and employment of on-line algorithms and stochastic optimization techniques allowing field researchers to assess the computational and accuracy trade-offs without compromising the data collection process Eventually, results from intelligent, open-access systems could offer significant societal benefits by raising public awareness of natural phenomena and exposing possible hazardous interactions between wildlife and humans allowing for swift mitigation procedures Proc. of the 1st Workshop on machine Learning for bioacoustics glotin et al. Ed, 2013 An additional, yet critical issue in present bioacoustic analysis strategies is the inability to provide comprehensive, accurate species validation across the full suite of signals available in very large sets of raw data. The process of extracting ground-truth, typically involves manual interaction by experts, which is an intractable task. This inherent bottleneck significantly limits our ability to identify a spccics'complctc signal variability across thc multiple dimensions of its acoustic signals, which thereby constrains our ability to process data at scales commensurate with the spatial-temporal-spectral biodiversity needs The application of advanced, unsupervised learning algorithms offers a possible solution to this problem because it would enable rapid computational access into the unique, underlying characteristics of the species-specific features, which would accelerate the recognition task Successful completion of this stage could then be combincd with supervised methodologies to yield a robust, iterative system for automatically processing very large amounts of data and visualizing those data products over appropriate ecological scales Moreover, automatic and accurate species recognition remains a top priority in the field This is a highly complex and challenging task. To be effective it needs to mirror the complexities of the hierarchical acoustic structures so often found within animal acoustic signaling behaviors, which would involve the application of both discriminative and generative approaches. Depending on the type of species under study, shallow or deep architectures might be favored. However, the diversities of the vocalization repertoires of the different species combined with their underlying biological structures indicate that any analysis and modeling would greatly benefit by integrating sparse constraints in order to increase the discriminative power of the models Finally, thc lack of standardization and unified comparative framework, combined with thc different environments and contexts of large scale data collection creates a unique domain adaptation and transfer learning framework whereby the proposed machine learning methodologies need to provide an adequate intra-and inter-species generalization In conclusion, the application of machine learning processes to bioacoustic sigi recognition analysis and modeling of large data scts promises to yicld significant thcorctical and applied advances in present understandings of complex, learned animal vocal behaviors and in the quantitative description of biodiversity over ecologically meaningful spatio temporal-spectral scales Proc. of the 1st Workshop on machine Learning for bioacoustics glotin et al. Ed, 2013 1.3. Workshop objectives The main objectives of this workshop are two-fold 1. Firstly, the workshop aims at bringing together experts from the machine learning and computational auditory scene analysis fields with experts in the field of animal acoustic communication systems to promote, discuss and explore the use of machine learning techniques in bioacoustics 2. Secondly, by presenting current approaches, their limitations and open problems in bioacoustics to the ICML community, this workshop will encourage interdisciplinary, scientific exchanges and foster collaborations among the workshop participants The proposed workshop is organized jointly by experts in the ficld of animal bioacoustics digital signal processing and machine learning and depending on participation rates, it will take place over two days. The target audience covers researchers working in the fields of bioacoustics signal analysis and detection-classilication, as well as researchers from the whole ICml community sharing an interest in real-world applications ranging from natural to cultural sounds. Given the combined participation of computer scientists and bioacousticians, the invited spcakcrs will bc asked to give talks with a tutorial charactcr and make the covered material accessible for both communities A special technical challenge on automated computer recognition of bird and marine mammal sounds will be organized in order to foster a common, quantitative framework bridging the two communities, while creating an initial, open-access and standardized data library for the communities The proposal and all future additional information can be found on line at http://sabiod.univ-tin.fr Proc. of the 1st Workshop on machine Learning for bioacoustics glotin et al. Ed, 2013

...展开详情
试读 104P ICML 2013国际会议论文集论文
立即下载 低至0.43元/次 身份认证VIP会员低至7折
一个资源只可评论一次,评论内容不能少于5个字
noel_ettoi 不错不错,很有用,找一些比较感兴趣的topic
2015-12-04
回复
您会向同学/朋友/同事推荐我们的CSDN下载吗?
谢谢参与!您的真实评价是我们改进的动力~
上传资源赚积分or赚钱
    最新推荐
    ICML 2013国际会议论文集论文 10积分/C币 立即下载
    1/104
    ICML 2013国际会议论文集论文第1页
    ICML 2013国际会议论文集论文第2页
    ICML 2013国际会议论文集论文第3页
    ICML 2013国际会议论文集论文第4页
    ICML 2013国际会议论文集论文第5页
    ICML 2013国际会议论文集论文第6页
    ICML 2013国际会议论文集论文第7页
    ICML 2013国际会议论文集论文第8页
    ICML 2013国际会议论文集论文第9页
    ICML 2013国际会议论文集论文第10页
    ICML 2013国际会议论文集论文第11页
    ICML 2013国际会议论文集论文第12页
    ICML 2013国际会议论文集论文第13页
    ICML 2013国际会议论文集论文第14页
    ICML 2013国际会议论文集论文第15页
    ICML 2013国际会议论文集论文第16页
    ICML 2013国际会议论文集论文第17页
    ICML 2013国际会议论文集论文第18页
    ICML 2013国际会议论文集论文第19页
    ICML 2013国际会议论文集论文第20页

    试读结束, 可继续阅读

    10积分/C币 立即下载 >