Speech recognition - PDFSEARCH.IO - Document Search Engine

Speech recognition
Results: 3329

#	Item
971	Speech enhancement by low-rank and convolutive dictionary spectrogram decomposition Zhuo Chen1,2 , Brian McFee1 , Daniel P. W. Ellis1,2 1 2 Add to Reading List Source URL: bmcfee.github.io Language: English - Date: 2015-03-31 11:15:28 Computational linguistics Digital signal processing Linear algebra Matrix theory Non-negative matrix factorization Noise reduction Speech enhancement Speech recognition PESQ Statistics Mathematics Signal processing
972	Towards an oral interface for data entry: The MAUD System Fohr, J.-P. Haton, J.-F. Mari, K. Smaïli and I. Zitouni CRIN-CNRS/ INRIA Lorraine BP239Vandoeuvre Lès-Nancy France e-mail: {fohr, jph, jfmari,smaili, zit Add to Reading List Source URL: ui4all.ics.forth.gr Language: English - Date: 2007-11-27 14:03:43 Speech recognition Natural language processing Markov models Corpus linguistics N-gram Language model Acoustic model Markov chain Syntax Linguistics Computational linguistics Science
973	IS S U E N o 3 / OCTOBERAMI Quarterly Newsletter Editor: Céline Aymon E-mail: - AMI @ a glance Add to Reading List Source URL: www.amiproject.org Language: English - Date: 2009-01-21 05:42:44 Idiap Research Institute Martigny Speech recognition Ambient intelligence W3C MMI International Computer Science Institute Speech processing Humanâ€“computer interaction Computing Multimodal interaction
974	Video Captioning ADA compliant captions: Are one to three (preferably two) lines of text that appear on-screen all at once o Have no more than 32 characters to a line Appear on screen for 2 to 6 seconds Are timed to sync Add to Reading List Source URL: www.pcc.edu Language: English - Date: 2012-03-26 19:51:59 Software Deafness Transcription Screencasting software Closed captioning Camtasia Studio Subtitle Speech recognition Assistive technology Accessibility Subtitling
975	Special Issue / April 2005 Editor : Céline Aymon, su s I Add to Reading List Source URL: www.amiproject.org Language: English - Date: 2009-01-21 05:42:44 Multimodal interaction Speech recognition Collaboratory Science Humanâ€“computer interaction Technology Interactive Multimodal Information Management Idiap Research Institute Martigny Ambient intelligence
976	REGULARIZATION, ADAPTATION, AND NON-INDEPENDENT FEATURES IMPROVE HIDDEN CONDITIONAL RANDOM FIELDS FOR PHONE CLASSIFICATION Yun-Hsuan Sung,1 Constantinos Boulis,2 Christopher Manning,3 Dan Jurafsky4 Electrical Engineering Add to Reading List Source URL: nlp.stanford.edu Language: English - Date: 2007-10-14 22:19:15 Learning Pattern recognition Regularization Conditional random field Hidden Markov model Speech recognition Overfitting Limited-memory BFGS Early stopping Machine learning Statistics Artificial intelligence
977	IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING 1 The CALO Meeting Assistant System Gokhan Tur, Senior Member, IEEE, Andreas Stolcke, Senior Member, IEEE, Lynn Voss, Stanley Peters, Add to Reading List Source URL: www.eecs.qmul.ac.uk Language: English - Date: 2010-02-18 04:41:11 Artificial intelligence Natural language processing CALO SRI International Speech recognition Automatic summarization International Computer Science Institute Segmentation Speech segmentation Science Information science Computational linguistics
978	arXiv Natural Language Processing (almost) from Scratch Ronan Collobert Add to Reading List Source URL: wiki.inf.ed.ac.uk Language: English - Date: 2012-06-11 05:09:58 Natural language processing Chunking Word-sense disambiguation Named-entity recognition Part-of-speech tagging Search engine indexing Semantic role labeling Classifier Support vector machine Linguistics Computational linguistics Science
979	Feed Forward Pre-training for Recurrent Neural Network Language Models Siva Reddy Gangireddy, Fergus McInnes and Steve Renals Centre for Speech Technology Research, University of Edinburgh, UK , Add to Reading List Source URL: homepages.inf.ed.ac.uk Language: English - Date: 2014-10-07 17:17:06 Cybernetics Neuroscience Backpropagation through time Recurrent neural network Speech recognition N-gram Backpropagation Artificial neuron Connectionism Neural networks Computational neuroscience Science
980	Probabilistic Linear Discriminant Analysis with Bottleneck Features for Speech Recognition Liang Lu, Steve Renals Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK {liang.lu, s.renals}@ed.ac.u Add to Reading List Source URL: homepages.inf.ed.ac.uk Language: English - Date: 2014-10-07 17:17:05 Multivariate statistics Estimation theory Computer accessibility Speech recognition Generalized method of moments Linear discriminant analysis Hidden Markov model Speaker recognition Statistics Automatic identification and data capture Computational linguistics

UPDATE