Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition
Why is this work in the frame?
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Abstract
We propose a novel context-dependent (CD) model for large-vocabulary speech recognition (LVSR) that leverages recent advances in using deep belief networks for phone recognition. We describe a pre-trained deep neural network hidden Markov model (DNN-HMM) hybrid architecture that trains the DNN to produce a distribution over senones (tied triphone states) as its output. The deep belief network pre-training algorithm is a robust and often helpful way to initialize deep neural networks generatively that can aid in optimization and reduce generalization error. We illustrate the key components of our model, describe the procedure for applying CD-DNN-HMMs to LVSR, and analyze the effects of various modeling choices on performance. Experiments on a challenging business search dataset demonstrate that CD-DNN-HMMs can significantly outperform the conventional context-dependent Gaussian mixture model (GMM)-HMMs, with an absolute sentence accuracy improvement of 5.8% and 9.2% (or relative error reduction of 16.0% and 23.2%) over the CD-GMM-HMMs trained using the minimum phone error rate (MPE) and maximum-likelihood (ML) criteria, respectively.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
The record
- Venue
- IEEE Transactions on Audio Speech and Language Processing
- Topic
- Speech Recognition and Synthesis
- Field
- Computer Science
- Canadian institutions
- University of Toronto
- Funders
- Microsoft ResearchUniversity of TorontoMicrosoft
- Keywords
- Hidden Markov modelComputer scienceSpeech recognitionWord error rateArtificial intelligenceArtificial neural networkContext (archaeology)Mixture modelDeep neural networksSentenceGeneralizationPhoneDeep learningPattern recognition (psychology)VocabularyMathematics
- Has abstract in OpenAlex
- yes