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.ed.ac.uk

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

LDC Forced Aligner Xiaoyi Ma Linguistic Data Consortium 3600 Market St. Suite 810 Philadelphia, PAE-mail:

Source URL: www.ldc.upenn.edu

• Computational linguistics
• Phonology
• Analytic languages
• English phonology
• Natural language processing
• CMU Pronouncing Dictionary
• Speech recognition
• Speech synthesis
• Acoustic model
• Standard Chinese
• Phoneme
• English language

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

Introduction to Multi-Waves Inverse Problems Quantitative Thermo-Acoustic Tomography (QTAT) Discussions on the System Model Quantitative thermo-acoustics and related problems

Source URL: www.math.purdue.edu

Cocaine Noodles: Exploiting the Gap between Human and Machine Speech Recognition∗ Tavish Vaidya Georgetown University Yuankai Zhang

Source URL: security.cs.georgetown.edu

• Computational linguistics
• Speech recognition
• Mel-frequency cepstrum
• Speech synthesis
• Speech processing
• Deep learning
• Perception
• Acoustic model

Analysis of CNN-based Speech Recognition System using Raw Speech as Input Dimitri Palaz1,2 , Mathew Magimai.-Doss1 , Ronan Collobert3,1 Idiap Research Institute, Martigny, Switzerland Ecole Polytechnique F´ed´erale de

Source URL: ronan.collobert.com

• Artificial neural networks
• Computational neuroscience
• Computational linguistics
• Applied mathematics
• Artificial intelligence
• Mathematics
• Signal processing
• Deep learning
• Convolutional neural network
• Speech recognition
• Acoustic model
• Mel-frequency cepstrum

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

MODELLING ACOUSTIC FEATURE DEPENDENCIES WITH ARTIFICIAL NEURAL NETWORKS: TRAJECTORY-RNADE Benigno Uria1 1 Iain Murray1

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

• Computational linguistics
• Speech recognition
• Acoustic model
• Artificial neural network
• Time series
• Speech synthesis
• Pattern recognition
• Machine learning
• Deep learning

Wed.P7b.02 Gaussian Map based Acoustic Model Adaptation Using Untranscribed Data for Speech Recognition in Severely Adverse Environments

Source URL: www.utdallas.edu

• Computational linguistics
• Automatic identification and data capture
• Computer accessibility
• Speech recognition
• Mixture model
• Hidden Markov model
• Speech corpus

AN ADVANCED FEATURE COMPENSATION METHOD EMPLOYING ACOUSTIC MODEL WITH PHONETICALLY CONSTRAINED STRUCTURE Wooil Kim1 and John H. L. Hansen2 1 2

Source URL: www.utdallas.edu

• Machine learning
• Artificial intelligence
• Learning
• Markov models
• Computer accessibility
• Speech recognition
• Mixture model
• Markov chain