Abstract
A crucial issue in triphone based continuous speech recognition is the large number of models to be estimated against the limited availability of training data. This problem can be relieved by composing a triphone model from less context-dependent models. This paper introduces a new statistical framework, derived from the Bayesian principle, to perform such a composition. The potential power of this new framework is explored, both algorithmically and experimentally, by an implementation with hidden Markov modeling techniques. This implementation is applied to the recognition of the 39-phone set on the TIMIT database. The new model achieves 74.4% and 75.6% accuracy, respectively, on the core and complete test sets.
Keywords
Computer scienceHidden Markov modelTIMITPhoneBayesian probabilityContext (archaeology)Speech recognitionArtificial intelligenceSet (abstract data type)Context modelMarkov modelMachine learningPattern recognition (psychology)Markov chain
Affiliated Institutions
Related Publications
Speech Recognition Using Augmented Conditional Random Fields
Acoustic modeling based on hidden Markov models (HMMs) is employed by state-of-the-art stochastic speech recognition systems. Although HMMs are a natural choice to warp the time...
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,...
An overlapping-feature-based phonological model incorporating linguistic constraints: Applications to speech recognition
Modeling phonological units of speech is a critical issue in speech recognition. In this paper, our recent development of an overlapping-feature-based phonological model that re...
Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition
Convolutional Neural Networks (CNN) have showed success in achieving translation invariance for many image processing tasks. The success is largely attributed to the use of loca...
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
- 2002
- Type
- article
- Volume
- 1
- Pages
- 409-412
- Citations
- 45
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
45
OpenAlex
Cite This
Ming Jiang,
F.J. Smith
(2002).
Improved phone recognition using Bayesian triphone models.
, 1
, 409-412.
https://doi.org/10.1109/icassp.1998.674454
Identifiers
- DOI
- 10.1109/icassp.1998.674454