N-gramモデルのエントロピーに基づくパラメータ削減に関する検討

IR IPSJ HANDLE Web Site 22 References Open Access

Bibliographic Information

Other Title
  • N gram モデル ノ エントロピー ニ モトヅク パラメータ サクゲン ニ カンスル ケントウ
  • A Study on Entropy-based Compression Algorithms for N-gram Parameters

Search this article

Abstract

Large vocabulary continuous speech recognition (LVCSR), which is simply called as dictation, is an essential technology for the realization of voice typing and interface between human being and a computer in various conditions. An LVCSR system reduces search space using language models, where statistical N-gram models are generally used. However, they need a huge number of parameters that grow exponentially with N and the vocabulary size. Especially in the task with large vocabulary (from a few thousand of words to several ten thousands of words), their huge memory requirement results in the system implementation difficulty. In this paper we compare algorithms for reducing the number of parameters of an N-gram model. Preliminary experiments on the augmentation of our compression algorithm to deal with (N-1)-gram are carried out.

Journal

References(22)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top