Deep neural network context embeddings for model selection in rich-context HMM synthesis Thomas Merritt1 , Junichi Yamagishi1,2 , Zhizheng Wu1 , Oliver Watts1 , Simon King1 1 The Centre for Speech Technology Research, U

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

• Computational linguistics
• Markov models
• Automatic identification and data capture
• Computer accessibility
• Speech recognition
• Speech synthesis
• Hidden Markov model
• KullbackLeibler divergence

Stochastic Pronunciation Modelling for Spoken Term Detection Dong Wang, Simon King, Joe Frankel The Centre for Speech Technology Research, University of Edinburgh, UK , ,

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

AN ASYNCHRONOUS DBN FOR AUDIO-VISUAL SPEECH RECOGNITION Kate Saenko and Karen Livescu Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge, USA, 02139 ABSTRACT

Source URL: ttic.uchicago.edu

Is the Stanford Dependency Representation Semantic? Rachel Rudinger1 and Benjamin Van Durme1,2 Center for Language and Speech Processing1 Human Language Technology Center of Excellence2 Johns Hopkins University rudinger@

Source URL: www.aclweb.org

• Linguistics
• Grammar
• Syntax
• Semantics
• Natural language processing
• Dependency grammar
• Natural language parsing
• Argument
• Parsing
• Predicate
• Natural language understanding

REGULARIZATION OF CONTEXT-DEPENDENT DEEP NEURAL NETWORKS WITH CONTEXT-INDEPENDENT MULTI-TASK TRAINING Peter Bell and Steve Renals Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB, UK ABST

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

• Artificial neural networks
• Machine learning
• Artificial intelligence
• Applied mathematics
• Speech recognition
• Boltzmann machine
• Recurrent neural network
• Multi-task learning
• Deep belief network
• Backpropagation
• Acoustic model
• Language model

Distributed Speech Processing over Wireless Mesh Networks Rajesh M. Hegde* and B. S. Manojt *Indian Institute of Technology Kanpur, India E-mail: rhegde@iitk. ac.in tIndian Institute of Space Science and Technology, Triv

Source URL: home.iitk.ac.in

Learning Speaker-Specific Phrase Breaks for Text-to-Speech Systems Kishore Prahallad1,2 , E. Veera Raghavendra1 , Alan W BlackInternational Institute of Information Technology, Hyderabad, India.

Source URL: ravi.iiit.ac.in

THE TEMPORAL DELAY HYPOTHESIS: NATURAL, VOCODED AND SYNTHETIC SPEECH Mirjam Wester1 , Martin Corley2 , Rasmus Dall1 1 The Centre for Speech Technology Research, The University of Edinburgh, UK

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

• Phonetics
• Cognition
• Computational linguistics
• Speech and language pathology
• Speech
• Speech disfluency
• Speech synthesis
• Speech perception
• Prosody
• Psycholinguistics

Observation Process Adaptation for Linear Dynamic Models Joe Frankel and Simon King Centre for Speech Technology Research University of Edinburgh 2 Buccleuch Place

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

TREASON, TECHNOLOGY, AND FREEDOM OF EXPRESSION Tom W. Bell† ABSTRACT: The power to punish treason against the U.S. conflicts with the First Amendment freedoms of speech and of the press. Far from a question of mere the

Source URL: www.tomwbell.com