Loading...
Please wait, while we are loading the content...
Similar Documents
Sequence labelling in structured domains with hierarchical recurrent neural networks (2007)
| Content Provider | CiteSeerX |
|---|---|
| Author | Fernández, Santiago Graves, Alex Schmidhuber, Jürgen |
| Description | Modelling data in structured domains requires establishing the relations among patterns at multiple scales. When these patterns arise from sequential data, the multiscale structure also contains a dynamic component that must be modelled, particularly, as is often the case, if the data is unsegmented. Probabilistic graphical models are the predominant framework for labelling unsegmented sequential data in structured domains. Their use requires a certain degree of a priori knowledge about the relations among patterns and about the patterns themselves. This paper presents a hierarchical system, based on the connectionist temporal classification algorithm, for labelling unsegmented sequential data at multiple scales with recurrent neural networks only. Experiments on the recognition of sequences of spoken digits show that the system outperforms hidden Markov models, while making fewer assumptions about the domain. |
| File Format | |
| Language | English |
| Publisher Date | 2007-01-01 |
| Publisher Institution | IN PROC. 20TH INT. JOINT CONF. ON ARTIFICIAL INTELLIGENCE, IJCAI 2007 |
| Access Restriction | Open |
| Subject Keyword | Connectionist Temporal Classification Algorithm Priori Knowledge Sequence Labelling Structured Domain Hierarchical System Spoken Digit Probabilistic Graphical Model Predominant Framework Multiscale Structure Hierarchical Recurrent Neural Network Multiple Scale Dynamic Component Recurrent Neural Network Sequential Data Certain Degree Hidden Markov Model Unsegmented Sequential Data |
| Content Type | Text |
| Resource Type | Article |
