An efficient search space representation for large vocabulary continuous speech recognition

Kris DemuynckpJacques Duchateau; Dirk Van Compernolle 20f

首页> 外文期刊>Speech Communication >An efficient search space representation for large vocabulary continuous speech recognition

【24h】

An efficient search space representation for large vocabulary continuous speech recognition

机译：用于大词汇量连续语音识别的有效搜索空间表示

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

In pursuance of better performance, current speech recognition systems tend to use more and more complicated models for both the acoustic and the language component, Cross-word context dependent (CD) phone models and long-span statistical language models (LMs) are now widely used. In this paper, we present a memory-efficient search topology that enables the use of such detailed acoustic and language models in a one pass time-synchronous recognition system. Characteristic of our approach is (1) the decoupling of the two basic knowledge sources. Namely pronunciation information and LM information, and (2) the representation of pronunciation information-the lexicon in terms of CD units-by means of a compact static network.

机译：为了获得更好的性能，当前的语音识别系统倾向于对声学和语言组件使用越来越复杂的模型，现在，跨字上下文相关（CD）电话模型和大跨度统计语言模型（LM）广泛使用用过的。在本文中，我们提出了一种内存有效的搜索拓扑结构，该拓扑结构可以在单程时间同步识别系统中使用此类详细的声学和语言模型。我们的方法的特点是（1）两个基本知识源的分离。即语音信息和LM信息，以及（2）语音信息的表示-通过紧凑的静态网络表示的CD单元形式的词典。

著录项

来源
《Speech Communication》 |2000年第1期|p.37-53|共17页
作者
Kris DemuynckpJacques Duchateau; Dirk Van Compernolle 20f;
展开▼
作者单位

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类语言、文字;
关键词

相似文献

外文文献
中文文献
专利

1. Large-Vocabulary Continuous Speech Recognition Using Linear Lexicon Search and 1-Best Approximation Tree-Structured Lexicon Search [J] . Norihide Kitaoka, Nobutoshi Takahashi, Seiichi Nakagawa Systems and Computers in Japan . 2005,第7期

机译：使用线性词典搜索和1-最佳逼近树结构词典搜索的大词汇量连续语音识别
2. Large vocabulary continuous speech recognition using N-best linear lexicon search and tree lexicon search with 1-best approximation [J] . Norihide Kitaoka, Nobutoshi Takahashi, Seiichi Nakagawa 電子情報通信学会技術研究報告. 音声. Speech . 2003,第94期

机译：使用N最佳线性词典搜索和具有1最佳近似的树词典搜索的大词汇量连续语音识别
3. Large vocabulary continuous speech recognition using N-best linear lexicon search and tree lexicon search with 1-best approximation [J] . Norihide Kitaoka, Nobutoshi Takahashi, Seiichi Nakagawa 電子情報通信学会技術研究報告. 音声. Speech . 2003,第94期

机译：使用N-Best Linear Lexicon搜索和Tree Lexicon搜索的大词汇连续语音识别，使用1-最近似
4. An Efficient Lexical Tree Search for Large Vocabulary Continuous speech Recognition [C] . J.Ogaa, Y.Ariki 6th International Conference on Spoken Language Processing ICSLP 2000 Oct.16-Oct.20 2000 Beijing International Convention Center, Beijing, China . 2000

机译：大型词汇连续语音识别的有效词法树搜索
5. An Error Detection and Correction Framework to Improve Large Vocabulary Continuous Speech Recognition [D] . Zhou, Zhengyu 2009

机译：一种提高大词汇量连续语音识别能力的错误检测与纠正框架
6. Neural speech recognition: Continuous phoneme decoding using spatiotemporal representations of human cortical activity [O] . David A Moses, Nima Mesgarani, Matthew K Leonard, -1

机译：神经语音识别：使用人类皮层活动的时空表示进行连续音素解码
7. Architecture and Search Organization for Large Vocabulary Continuous Speech Recognition [O] . Stefan Ortmanns, Lutz Welling, Klaus Beulen, 2014

机译：大词汇量连续语音识别的体系结构和搜索组织

An efficient search space representation for large vocabulary continuous speech recognition

摘要

著录项

相似文献

相关主题

期刊订阅