In this paper we present a training method and a network architecture for estimating context-dependent observation probabilities in the framework of a hybrid hidden Markov model (HMM)/multi layer perceptron (MLP) speaker-independent continuous speech recognition system. The context-dependent modelin
Context-dependent probability adaptation in speech understanding
✍ Scribed by Erwin W Drenth; Bernhard Rüber
- Publisher
- Elsevier Science
- Year
- 1997
- Tongue
- English
- Weight
- 331 KB
- Volume
- 11
- Category
- Article
- ISSN
- 0885-2308
No coin nor oath required. For personal study only.
✦ Synopsis
By using context-dependent concept language models, we can significantly improve the performance of the speech understanding component of a dialogue system. We use several different modelling methods, such as bigrams, concept set probability estimations using graph theory and combinations of these. The contexts are selected both manually and automatically using mutual information. Using context-dependent bigrams, with contexts selected by the clustering algorithm, we establish a relative increase in performance of 10% on the attribute error rate on data obtained through the currently operational Swiss automatic train timetable information system.
📜 SIMILAR VOLUMES
## Abstract ## Background Adrenomedullin (AM) is a potent vasodilator and natriuretic peptide produced in the heart, but controversy persists regarding its cardiac effects. We explored the potential role of AM on cardiac function and remodeling by direct recombinant adenoviral AM gene delivery int