Maximum-likelihood continuity mapping (MALCOM): an alternative to HMMs
Proceedings of the 1998 conference on Advances in neural information processing systems II
Bayesian Networks and Decision Graphs
Bayesian Networks and Decision Graphs
Connectionist speech recognition of Broadcast News
Speech Communication - Special issue on automatic transcription of broadcast news data
A syllable, articulatory-feature, and stress-accent model of speech recognition
A syllable, articulatory-feature, and stress-accent model of speech recognition
The HDM: a segmental hidden dynamic model of coarticulation
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Distinctive feature detection using support vector machines
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
CasJoin: a cascade chain for text similarity joins
CIKM '10 Proceedings of the 19th ACM international conference on Information and knowledge management
Review: Statistical parametric speech synthesis
Speech Communication
A conditional independence algorithm for learning undirected graphical models
Journal of Computer and System Sciences
Discriminative input stream combination for conditional random field phone recognition
IEEE Transactions on Audio, Speech, and Language Processing
Integrating phonological knowledge in ASR systems for Spanish language
CIARP'10 Proceedings of the 15th Iberoamerican congress conference on Progress in pattern recognition, image analysis, computer vision, and applications
Improving articulatory feature and phoneme recognition using multitask learning
ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
Automatic analysis of Mandarin accented English using phonological features
Speech Communication
Hi-index | 0.00 |
We describe a dynamic Bayesian network for articulatory feature recognition. The model is intended to be a component of a speech recognizer that avoids the problems of conventional ''beads-on-a-string'' phoneme-based models. We demonstrate that the model gives superior recognition of articulatory features from the speech signal compared with a state-of-the-art neural network system. We also introduce a training algorithm that offers two major advances: it does not require time-aligned feature labels and it allows the model to learn a set of asynchronous feature changes in a data-driven manner.