AUDIOVISUAL SPEECH RECOGNITION WITH ARTICULATOR POSITIONS AS HIDDEN VARIABLES Mark Hasegawa-Johnson, Karen Livescu, Partha Lal and Kate Saenko∗ University of Illinois at Urbana-Champaign, MIT, University of Edinburgh,

Source URL: ttic.uchicago.edu

Senior Executive Service Class Graduation Speech December 2008 Good morning! I am profoundly honored to join this outstanding group of civil servants. I’d like to offer a very special recognition of Bob Ashworth, who w

Source URL: www.lynnscarlett.com

Demonstration & Toolkit Call for Proposals The program committee for the 14th biannual IEEE workshop on Automatic Speech Recognition and Understanding is accepting proposals for the Demo & Toolkit session that will be he

Source URL: www.asru2015.org

Continuous Speech Recognition using Joint Features derived from The Modified Group Delay Function and MFCC Gadde V. Ramana Rao Rajesh M. Hegde, Hema A. Murthy Department of Computer Science and Engineering

Source URL: home.iitk.ac.in

Significance of Group Delay based Acoustic Features in the Linguistic Search Space for Robust Speech Recognition Ramya R1 , Rajesh M Hegde2 , Hema A Murthy1 1 Indian Institute of Technology Madras,

Source URL: home.iitk.ac.in

Curriculum Vitae Geoffrey E. Hinton July 14, 2015 Citizenship: Canadian (also British) Address:

Source URL: www.cs.toronto.edu

• Artificial neural networks
• Cognitive science
• Machine learning
• Academia
• Computational neuroscience
• Cybernetics
• Geoffrey Hinton
• Boltzmann machine
• Deep learning
• Speech recognition
• Artificial intelligence
• Helmholtz machine

ALISA: An Automatic Lightly Supervised Speech Segmentation and Alignment ToolI A. Stana,1 , Y. Mamiyab , J. Yamagishia,c , P. Bellb , O. Wattsb , R.A.J. Clarkb , S. Kingb a Communications

Source URL: www.cstr.ed.ac.uk

• Computational linguistics
• Humancomputer interaction
• Artificial intelligence
• Speech recognition
• Software
• Natural language processing
• Computer accessibility
• Speech synthesis
• Acoustic model
• Speech segmentation
• Language model
• Image segmentation

Fusion of multiple parameterisations for DNN-based sinusoidal speech synthesis with multi-task learning Qiong Hu1 , Zhizheng Wu1 , Korin Richmond1 , Junichi Yamagishi1 , Yannis Stylianou2 , Ranniery Maia2 1 The Centre f

Source URL: www.cstr.ed.ac.uk

• Music
• Computational linguistics
• Audio electronics
• Artificial intelligence
• Music hardware
• Robotics
• Vocoder
• Speech recognition
• Speech synthesis
• Synthesizer
• Artificial neural network
• Frequency modulation

FEATURE COMPENSATION EMPLOYING ONLINE GMM ADAPTATION FOR SPEECH RECOGNITION IN UNKNOWN SEVERELY ADVERSE ENVIRONMENTS Wooil Kim and John H. L. Hansen Center for Robust Speech Systems (CRSS), Erik Jonsson School of Enginee

Source URL: www.utdallas.edu

• Linguistics
• Automatic identification and data capture
• Humancomputer interaction
• Speech recognition
• Human communication
• Computational linguistics
• Computer accessibility
• FMLLR
• Speech enhancement
• Cepstrum
• Speech corpus

Learning Hidden Markov Models Using Back-Propagation through Time Hiroshi Mamitsuka

Source URL: www.jsbi.org

• Markov models
• Machine learning
• Applied mathematics
• Statistics
• BaumWelch algorithm
• Speech recognition
• Hidden Markov model
• Recurrent neural network
• Expectationmaximization algorithm
• Artificial neural network