SUBMITTED TO IEEE TRANS. ON AUDIO, SPEECH, AND LANGUAGE PROCESSING 1 Acoustic Modeling using Deep Belief Networks Abdel-rahman Mohamed, George E. Dahl, and Geoffrey Hinton

Source URL: www.cs.toronto.edu

• Science
• Artificial neural network
• Boltzmann machine
• Recurrent neural network
• Feedforward neural network
• Backpropagation
• Speech recognition
• Hidden Markov model
• Early stopping
• Neural networks
• Machine learning
• Cybernetics

ADAPTATION OF PRECISION MATRIX MODELS ON LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION K.C. Sim and M.J.F. Gales Engineering Department, Cambridge University, Trumpington St., Cambridge, CB2 1PZ U.K. Email: {kcs23,mjfg}

Source URL: mi.eng.cam.ac.uk

• Data analysis
• Estimation theory
• Matrix
• Covariance
• Multivariate normal distribution
• Maximum likelihood
• Principal component analysis
• Kalman filter
• Statistics
• Algebra
• Covariance and correlation

Transport Research Arena 2014, Paris Analysis and classification of Powered Two Wheelers riding pattern Ferhat Attala*, Abderrahmane bderrahmane Boubezoula, Latifa Oukhelloub and Stéphane Espiéc a

Source URL: tra2014.traconference.eu

• Learning
• Statistical classification
• Parts of speech
• Classifier
• Support vector machine
• Supervised learning
• Pattern recognition
• Random subspace method
• Boosting methods for object categorization
• Machine learning
• Statistics
• Artificial intelligence

INTERSPEECHDetecting Pitch Accent Using Pitch-corrected Energy-based Predictors Andrew Rosenberg, Julia Hirschberg Computer Science Department, Columbia University, USA {amaxwell,julia}@cs.columbia.edu

Source URL: www1.cs.columbia.edu

• Computational linguistics
• Tone
• Prosody
• Pitch accent
• Word-sense disambiguation
• Speech synthesis
• Speech recognition
• Pitch
• Stress
• Linguistics
• Phonology
• Phonetics

Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine George E. Dahl, Marc’Aurelio Ranzato, Abdel-rahman Mohamed, and Geoffrey Hinton Department of Computer Science University of Toronto {gdahl, ranza

Source URL: www.cs.toronto.edu

• Markov models
• Statistical models
• Data analysis
• Neural networks
• Speech recognition
• Hidden Markov model
• Boltzmann machine
• Principal component analysis
• Covariance matrix
• Statistics
• Probability and statistics
• Machine learning

Adaptive Training for Large Vocabulary Continuous Speech Recognition Kai Yu Hughes Hall College

Source URL: svr-www.eng.cam.ac.uk

• Statistical models
• Estimation theory
• Bayesian statistics
• Hidden Markov model
• Speech recognition
• Expectation–maximization algorithm
• Bayesian network
• Variational Bayesian methods
• Mixture model
• Statistics
• Machine learning
• Markov models

IEEE-28MSP01-Feature-TEMPLATE

Source URL: www.cs.toronto.edu

• Computational neuroscience
• Science
• Computational statistics
• Computational linguistics
• Hidden Markov model
• Boltzmann machine
• Speech recognition
• Artificial neural network
• Backpropagation
• Neural networks
• Statistics
• Machine learning

BASIS SUPERPOSITION PRECISION MATRIX MODELLING FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION K.C. Sim and M.J.F. Gales Engineering Department, Cambridge University, Trumpington St., Cambridge, CB2 1PZ U.K. Email: {k

Source URL: mi.eng.cam.ac.uk

Training and Evaluating a German Named Entity Recognizer with Semantic Generalization Manaal Faruqui Dept. of Computer Science and Engineering Indian Institute of Technology Kharagpur, India

Source URL: www.nlpado.de

• Computational linguistics
• Named-entity recognition
• Part-of-speech tagging
• International Corpus of English
• Precision and recall
• Recall
• Generalization
• Linguistics
• Science
• Natural language processing

DEVELOPMENT OF THE CU-HTK 2004 BROADCAST NEWS TRANSCRIPTION SYSTEMS D.Y. Kim, H.Y. Chan, G. Evermann, M.J.F. Gales, D. Mrva, K.C. Sim, P.C. Woodland Engineering Department, Cambridge University, Trumpington St., Cambridg

Source URL: mi.eng.cam.ac.uk

• Machine learning
• Test set
• Human–computer interaction
• Artificial intelligence
• Science
• Automatic identification and data capture
• Computer accessibility
• Speech recognition