Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

Learning representations by back-propagating errors

1986 • 25,825 citations

Reducing the Dimensionality of Data with Neural Networks

2006 • 18,756 citations

A Fast Learning Algorithm for Deep Belief Nets

2006 • 15,378 citations

Understanding the difficulty of training deep feedforward neural networks

2010 • 11,866 citations

Advances in Neural Information Processing Systems 19

2007 • 9,326 citations

Extracting and composing robust features with denoising autoencoders

2008 • 6,787 citations

Learning Deep Architectures for AI

2009 • 6,498 citations

A unified architecture for natural language processing

2008 • 5,201 citations

Learning Deep Architectures for AI

2009 • 5,200 citations

Training Products of Experts by Minimizing Contrastive Divergence

2002 • 4,852 citations

Why Does Unsupervised Pre-training Help Deep Learning?

2010 • 2,144 citations

What is the best multi-stage architecture for object recognition?

2009 • 2,137 citations

Acoustic Modeling Using Deep Belief Networks

2011 • 1,722 citations

Information processing in dynamical systems: foundations of harmony theory

1986 • 1,646 citations

Semantic hashing

2008 • 1,266 citations

Connectionist Speech Recognition: A Hybrid Approach

1993 • 1,161 citations

Scaling learning algorithms towards AI

2007 • 945 citations

Deep learning via Hessian-free optimization

2010 • 755 citations

Tandem connectionist feature extraction for conventional HMM systems

2002 • 695 citations

Minimum Phone Error and I-smoothing for improved discriminative training

2002 • 641 citations

Minimum classification error rate methods for speech recognition

1997 • 632 citations

Why Does Unsupervised Pre-training Help Deep Learning?

2010 • 618 citations

Connectionist Speech Recognition

1994 • 566 citations

Learning to Detect Roads in High-Resolution Aerial Images

2010 • 563 citations

Large-Scale Kernel Machines

2007 • 530 citations

Exponential Family Harmoniums with an Application to Information Retrieval

2004 • 443 citations

Mean and variance adaptation within the MLLR framework

1996 • 402 citations

The Recurrent Temporal Restricted Boltzmann Machine

2008 • 373 citations

Scaling Learning Algorithms toward AI

2007 • 363 citations

Boosted MMI for model and feature-space discriminative training

2008 • 353 citations

Probabilistic and Bottle-Neck Features for LVCSR of Meetings

2007 • 344 citations

The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training

2009 • 319 citations

Hidden conditional random fields for phone classification

2005 • 308 citations

3D Object Recognition with Deep Belief Nets

2009 • 305 citations

Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine

2010 • 271 citations

Modeling pixel means and covariances using factorized third-order boltzmann machines

2010 • 241 citations

Developments and directions in speech recognition and understanding, Part 1 [DSP Education]

2009 • 231 citations

Connectionist probability estimators in HMM speech recognition

1994 • 226 citations

Investigation of full-sequence training of deep belief networks for speech recognition

2010 • 214 citations

The Curse of Highly Variable Functions for Local Kernel Machines

2005 • 190 citations

Roles of Pre-Training and Fine-Tuning in Context-Dependent DBN-HMMs for Real-World Speech Recognition

2010 • 190 citations

A survey of hybrid ANN/HMM models for automatic speech recognition

2001 • 187 citations

Large vocabulary continuous speech recognition with context-dependent DBN-HMMS

2011 • 184 citations

Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system

1995 • 183 citations

Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error

2006 • 173 citations

Continuous speech recognition using multilayer perceptrons with hidden Markov models

2002 • 170 citations

Discriminative learning in sequential pattern recognition

2008 • 143 citations

Optimizing bottle-neck features for lvcsr

2008 • 134 citations

On adaptive decision rules and decision parameter adaptation for automatic speech recognition

2000 • 131 citations

Large Margin Gaussian Mixture Modeling for Phonetic Classification and Recognition

2006 • 126 citations

Shared-distribution hidden Markov models for speech recognition

1993 • 125 citations

A segmental CRF approach to large vocabulary continuous speech recognition

2009 • 119 citations

Continuous speech recognition by connectionist statistical methods

1993 • 105 citations

Using MLP features in SRI's conversational speech recognition system

2005 • 100 citations

MMI training for continuous phoneme recognition on the TIMIT database

1993 • 98 citations

Pushing the envelope - aside [speech recognition

2005 • 96 citations

A unified framework of HMM adaptation with joint compensation of additive and convolutive distortions

2009 • 95 citations

A dynamic, feature-based approach to the interface between phonology and phonetics for speech modeling and recognition

1998 • 87 citations

Structured speech modeling

2006 • 86 citations

Speech Recognition Using Augmented Conditional Random Fields

2009 • 83 citations

DECISION TREES DO NOT GENERALIZE TO NEW VARIATIONS

2010 • 81 citations

CUDAMat: a CUDA-based matrix class for Python

2009 • 69 citations

Live search for mobile:Web services by voice on the cellphone

2008 • 69 citations

CDNN: a context dependent neural network for continuous speech recognition

1992 • 67 citations

Large-Margin Minimum Classification Error Training for Large-Scale Speech Recognition Tasks

2007 • 57 citations

Connectionist speech recognition of Broadcast News

2002 • 57 citations

Automated directory assistance system - from theory to practice

2007 • 54 citations

Computational Models for Speech Production

1999 • 53 citations

Speech recognition using neural networks with forward-backward probability generated targets

2002 • 53 citations

An investigation of segmental hidden dynamic models of speech coarticulation for automatic speech recognition

1998 • 51 citations

Combining phonetic attributes using conditional random fields

2006 • 50 citations

Large Margin HMMs for Speech Recognition

2006 • 50 citations

Estimation of global posteriors and forward-backward training of hybrid HMM/ANN systems

1997 • 50 citations

Updated MINDS report on speech recognition and understanding, Part 2 [DSP Education]

2009 • 47 citations

Context-dependent connectionist probability estimation in a hybrid hidden Markov model-neural net speech recognition system

1994 • 46 citations

Transcribing broadcast data using MLP features

2008 • 43 citations

A Novel Framework and Training Algorithm for Variable-Parameter Hidden Markov Models

2009 • 39 citations

Deep-structured hidden conditional random fields for phonetic recognition

2010 • 38 citations

The Study of the Classification of Chinese Folk Songs by Regional Style

2007 • 37 citations

Development of the SRI/nightingale Arabic ASR system

2008 • 37 citations

Incorporating Training Errors for Large Margin HMMS Under Semi-Definite Programming Framework

2007 • 36 citations

Large-margin minimum classification error training: A theoretical risk minimization perspective

2008 • 35 citations

SCARF: a segmental conditional random field toolkit for speech recognition

2010 • 35 citations

A log-linear discriminative modeling framework for speech recognition.

2010 • 33 citations

A bidirectional target-filtering model of speech coarticulation and reduction: two-stage implementation for phonetic recognition

2005 • 28 citations

Speaker-adaptation in a hybrid HMM-MLP recognizer

2002 • 19 citations

A comparative large scale study of MLP features for Mandarin ASR

2010 • 18 citations

Use of incrementally regulated discriminative margins in MCE training for speech recognition

2006 • 18 citations

A Bidirectional Target Filtering Model of Speech Coarticulation: two-stage Implementation for Phonetic Recognition

2006 • 15 citations

Large-Margin Discriminative Training of Hidden Markov Models for Speech Recognition

2007 • 14 citations