The 2014 KIT IWSLT Speech-to-Text Systems for English, German and Italian Kevin Kilgour, Michael Heck, Markus M¨uller, Matthias Sperber, Sebastian St¨uker and Alex Waibel Institute for Anthropomatics Karlsruhe Institut

Source URL: isl.anthropomatik.kit.edu

• Computational linguistics
• Linguistics
• Language
• Artificial intelligence
• Speech recognition
• Speech synthesis
• CMU Pronouncing Dictionary
• Phoneme
• Machine translation
• N-gram
• Acoustic model
• Grapheme

Laughter detection using ALISP-based N-Gram models Sathish Pammi, Houssemeddine Khemiri and Gérard Chollet Telecom ParisTech, Rue Dareau, 37-39, 75014 Paris, France {firstname.lastname}@telecom-paristech.fr Laughter is

Source URL: www.ilhaire.eu

• Computational linguistics
• Speech recognition
• Markov models
• Laughter
• N-gram
• Acoustic model
• Language model
• Hidden Markov model
• Image segmentation

Proceedings of the Canadian Hydrographic Conference and National Surveyors Conference 2008 SHOALS3000 Surveying Above Dense Fields of Aquatic Vegetation – Quantifying and Identifying Bottom Tracking Issues

Source URL: omg.unb.ca

• Cartography
• Oceanography
• Lidar
• Robotic sensing
• Sonar
• Surveying
• Bathymetry
• Multibeam echosounder
• Hydrographic survey
• Laser
• Digital elevation model
• Acoustic seabed classification

Structured Output Layer with Auxiliary Targets for Context-Dependent Acoustic Modelling Pawel Swietojanski, Peter Bell, Steve Renals The Centre for Speech Technology Research, University of Edinburgh, United Kingdom {p.s

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

• Artificial neural networks
• Computational neuroscience
• Computational statistics
• Automatic identification and data capture
• Computer accessibility
• Speech recognition
• Language model
• Convolutional neural network
• Perceptron
• Recurrent neural network
• Machine learning
• Deep learning

ADIEU FEATURES? END-TO-END SPEECH EMOTION RECOGNITION USING A DEEP CONVOLUTIONAL RECURRENT NETWORK George Trigeorgis1 , Fabien Ringeval2,3 , Raymond Brueckner3,4 , Erik Marchi3 Mihalis A. Nicolaou5 , Björn Schuller1,2,6

Source URL: ibug.doc.ic.ac.uk

• Artificial neural networks
• Computational neuroscience
• Computational linguistics
• Cybernetics
• Computational statistics
• Deep learning
• Speech recognition
• Recurrent neural network
• Convolutional neural network
• Long short-term memory
• Acoustic model
• Affective computing

Microsoft Word - AES 129.doc

Source URL: www.j3l7h.de

• Audio codecs
• Code-excited linear prediction
• Speech coding
• Speex
• G.711
• Acoustic model
• Unified Speech and Audio Coding

A SYSTEM FOR AUTOMATIC ALIGNMENT OF BROADCAST MEDIA CAPTIONS USING WEIGHTED FINITE-STATE TRANSDUCERS Peter Bell and Steve Renals Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB, UK {pete

Source URL: homepages.inf.ed.ac.uk

• Computational linguistics
• Speech recognition
• Acoustic model
• Alignment
• Speech synthesis
• Closed captioning
• Word error rate
• Word-sense disambiguation
• Language model
• Finite-state transducer

Prosodically-enhanced Recurrent Neural Network Language Models Siva Reddy Gangireddy and Steve Renals Yoshihiko Nankaku and Akinobu Lee Centre for Speech Technology Research

Source URL: homepages.inf.ed.ac.uk

• Computational linguistics
• Phonology
• Phonetics
• Systemic functional linguistics
• Speech recognition
• Prosody
• Language model
• Acoustic model
• Artificial neural network
• Recurrent neural network
• Intonation
• Syllable

A Hidden Markov Model-Based Acoustic Cicada Detector for Crowdsourced Smartphone Biodiversity Monitoring

Source URL: www.orchid.ac.uk

WORD PERFECT TEMPLATE FOR CAA-ACA PROCEEDINGS PAPER: 14-PT FONT

Source URL: prosodylab.org

• Computational linguistics
• Humancomputer interaction
• Speech recognition
• Acoustic model
• Software
• Human communication
• HTK