Abstract
Recently, Deep Belief Networks (DBNs) have been proposed for phone recognition and were found to achieve highly competitive performance. In the original DBNs, only framelevel information was used for training DBN weights while it has been known for long that sequential or full-sequence information can be helpful in improving speech recognition accuracy. In this paper we investigate approaches to optimizing the DBN weights, state-to-state transition parameters, and language model scores using the sequential discriminative training criterion. We describe and analyze the proposed training algorithm and strategy, and discuss practical issues and how they affect the final results. We show that the DBNs learned using the sequence-based training criterion outperform those with frame-based criterion using both threelayer and six-layer models, but the optimization procedure for the deeper DBN is more difficult for the former criterion.
Keywords
Computer scienceTraining (meteorology)Speech recognitionSequence (biology)Artificial intelligenceNatural language processing
Affiliated Institutions
Related Publications
Comparing multilayer perceptron to Deep Belief Network Tandem features for robust ASR
In this paper, we extend the work done on integrating multilayer perceptron (MLP) networks with HMM systems via the Tandem approach. In particular, we explore whether the use of...
Deep Belief Networks using discriminative features for phone recognition
Deep Belief Networks (DBNs) are multi-layer generative models. They can be trained to model windows of coefficients extracted from speech and they discover multiple layers of fe...
Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling
Acoustic models used in hidden Markov model/neural-network (HMM/NN) speech recognition systems are usually trained with a frame-based cross-entropy error criterion. In contrast,...
Boosting attribute and phone estimation accuracies with deep neural networks for detection-based speech recognition
Generation of high-precision sub-phonetic attribute (also known as phonological features) and phone lattices is a key frontend component for detection-based bottom-up speech rec...
Backpropagation training for multilayer conditional random field based phone recognition
Conditional random fields (CRFs) have recently found increased popularity in automatic speech recognition (ASR) applications. CRFs have previously been shown to be effective com...
Publication Info
- Year
- 2010
- Type
- article
- Citations
- 213
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
213
OpenAlex
Cite This
Abdelrahman Mohamed,
Dong Yu,
Li Deng
(2010).
Investigation of full-sequence training of deep belief networks for speech recognition.
.
https://doi.org/10.21437/interspeech.2010-304
Identifiers
- DOI
- 10.21437/interspeech.2010-304