2011 · 638 citations · 17 references
ComputingComputer ScienceFeature EngineeringMachine LearningNatural Language ProcessingAcoustic PhoneticsDeep LearningPhonetic TranscriptionSpeech AcousticsSpeech RecognitionError Rate AnalysisError Rate MetricsFeature Vector EngineeringGaussian Mixture ModelsPhoneme RecognitionSpeaker-independent Speech RecognitionStatistical Feature EngineeringWord Error Rate
We investigate the potential of Context-Dependent Deep-Neural-Network HMMs, or CD-DNN-HMMs, from a feature-engineering perspective. Recently, we had shown that for speaker-independent transcription of phone calls (NIST RT03S Fisher data), CD-DNN-HMMs reduced the word error rate by as much as one third-from 27.4%, obtained by discriminatively trained Gaussian-mixture HMMs with HLDA features, to 18.5%-using 300+ hours of training data (Switchboard), 9000+ tied triphone states, and up to 9 hidden network layers.
17
Learning representations by back-propagating errors
David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams · Nature · 1986 · 30.9K citations
A Fast Learning Algorithm for Deep Belief Nets
Geoffrey E. Hinton, Simon Osindero, Yee‐Whye Teh · Neural Computation · 2006 · 16.4K citations