权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Speech Recognition Based on Intelligent Beam Search Algorithm

基于智能波束搜索算法的语音识别

基本信息

批准号：
01460254
负责人：
KOHDA Masaki
金额：
$ 4.42万
依托单位：
Yamagata University
依托单位国家：
日本
项目类别：
Grant-in-Aid for General Scientific Research (B)
财政年份：
1989
资助国家：
日本
起止时间：
1989 至 1991
项目状态：
已结题

来源：
https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-01460254/
关键词：
Speech Recognition Graph Search A^* Algorithm Dynamic Time Warping Beam Search Vector Quantization Hidden Markov Model Best-First Search DPマッチング予備選択 DPビ-ムサ-チ閾値関数枝刈フレ-ム同期DPマッチング

项目摘要

In a large-vocabulary continuous speech recognition, an investigation of efficient recognition algorithms is extremely important because of executing an enormous computation needed in a matching process within a realistic CPU time. Conventional recognition algorithms based on a dynamic time warping (DTW), a hidden Markov model (HMM) and so on are constructed on the base of an exhaustive search of possible combinations. A dynamic programming technique is introduced to execute the exhaustive search efficiently.The matching process in DTW-based and HMM-based speech recognition systems is regarded as a problem of searching an optimal path through a constrained node. In an application of graph searching algorithms to speechrecognition, two kinds of searching algorithms are effective, that is, a beam searching algorithm and a best-first searching algorithm. A conventional pruning strategy in speech recognition using the beam searching algorithm is based on only a score from the beginning node to the current node. A score estimate from the current node to the terminal node is not used. An A^* algorithm is introduced to speech recognition using the best-first searching algorithm.This report describes new approaches to DTW-based and HMM-based speech recognition algorithms by modeling the matching process from a view point of a graph search. In Chapter I, a DTW-based speech recognition utilizing the beam searching algorithm is described. In Chapter II, a DTW-based speech recognition utilizing the best-first searching algorithm is described. Finally in Chapter III, an HMM-based speech recognition utilizing the best-first searching algorithm is described.

在大词汇量连续语音识别中，高效识别算法的研究是非常重要的，因为匹配过程需要在实际的CPU时间内执行大量的计算。传统的识别算法基于动态时间规整（DTW）、隐马尔可夫模型（HMM）等，是在穷尽搜索可能组合的基础上构建的。为了有效地执行穷举搜索，引入了动态规划技术。在基于dtw和基于hmm的语音识别系统中，匹配过程被认为是一个通过约束节点搜索最优路径的问题。在图搜索算法在语音识别中的应用中，有两种有效的搜索算法，即波束搜索算法和最佳优先搜索算法。传统的基于波束搜索算法的语音识别剪枝策略仅基于起始节点到当前节点的分数。不使用从当前节点到终端节点的分数估计。采用最佳优先搜索算法将A^*算法引入到语音识别中。本报告描述了基于dtw和基于hmm的语音识别算法的新方法，从图搜索的角度对匹配过程进行建模。第一章描述了一种基于波束搜索算法的dtw语音识别方法。第二章描述了一种基于dtw的基于最佳优先搜索算法的语音识别方法。最后，在第三章中，描述了一种基于hmm的语音识别方法。