11 search results - page 1 / 3 » Multi-Class Composite N-gram Language Model for Spoken Langu... |
ACL
2001
13 years 6 months ago
2001
In this paper, a new language model, the Multi-Class Composite N-gram, is proposed to avoid a data sparseness problem for spoken language in that it is difficult to collect traini...
ICASSP
2009
IEEE
13 years 2 months ago
2009
IEEE
In the context of spoken language interpretation, this paper introduces a stochastic approach to infer and compose semantic structures. Semantic frame structures are directly deri...
ACL
2009
13 years 2 months ago
2009
This paper presents a model for summarizing multiple untranscribed spoken documents. Without assuming the availability of transcripts, the model modifies a recently proposed unsup...
MODELS
2009
Springer
13 years 9 months ago
2009
Springer
Abstract. Predefined composite operations are handy for efficient modeling, e.g., for the automatic execution of refactorings, and for the introduction of patterns in existing mod...
CVPR
2009
IEEE
14 years 12 months ago
2009
IEEE
Recognition of signs in sentences requires a training
set constructed out of signs found in continuous sentences.
Currently, this is done manually, which is a tedious process.
I...