BROWSE
Detail
Conference Paper
Lattice Rescoring for Speech Recognition Using Large Scale Distributed Language Models
Cited - time in 
Share 
Share
- Authors
- Euisok Chung, Hyung-Bae Jeon, Jeon-Gue Park, Yun-Keun Lee
- Issue Date
- 2012-05
- Citation
- International Conference on Computational Linguistics (COLING) 2012, pp.217-224
- Language
- English
- Type
- Conference Paper
- Abstract
- In this paper, we suggest a lattice rescoring architecture that has features of a Trie DB based language model (LM) server and a naïve parameter estimation (NPE) to integrate distributed language models. The Trie DB LM server supports an efficient computation of LM score to rerank the n-best sentences extracted from the lattice. In the case of NPE, it has a role of an integration of heterogeneous LM resources. Our approach distributes LM computations not only to distribute LM resources. This is simple and easy to implement and maintain the distributed lattice rescoring architecture. The experimental results show that the performance of the lattice rescoring has improved with the NPE algorithm that can find the optimal weights of the LM interpolation. In addition, we show that it is available to integrate n-gram LM and DIMI LM.
- KSP Keywords
- Efficient computation, Language model, Parameter estimation, large-scale, n-gram LM, optimal weights, speech recognition