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

Algorithm of Spontaneous Speech Recognition Based on A^<**> Search

基于A^<**>搜索的自发语音识别算法

基本信息

批准号：
07680379
负责人：
KOHDA Masaki
金额：
$ 1.09万
依托单位：
Yamagata University
依托单位国家：
日本
项目类别：
Grant-in-Aid for Scientific Research (C)
财政年份：
1995
资助国家：
日本
起止时间：
1995 至 1996
项目状态：
已结题

来源：
https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-07680379/
关键词：
Speech Recognition Acoustic Model Language Model Hidden Markov Model Hidden Markov Net N-gram Phoneme Decision Tree Likelihood Normalization サーチ手法単語予備選択

项目摘要

Spontaneous speech recognition is regarded as a problem of graph search considering various restrictions through acoustic model, lexicon, language model and so on. In order to reduce a computation amount for recognition processing without degradation of recognition performance, some key technologies of spontaneous speech recognition were investigated.(1) Acoustic model and speaker adaptationThe important aspects of context-dependent acoustic modeling using a limited training data set are how to tie the model parameters and how to handle the unseen contexts. We proposed the decision tree-based successive state splitting algorithm, and showed that HM-Net generated with this algorithm had high accuracy and enabled to represent any contexts. Speaker adaptation of acoustic model parameters based on MAP estimation method was also investigated.(2) Fast matching and likelihood normalizationIn large vocabulary word recognition, a fast preselection of word candidates was investigated. Phoneme recognition of input speech was carried out and an optimal phoneme sequence was obtained from the input speech. To select word candidates, DP matching was executed with the optimal phoneme sequence. The word candidates were verified by Viterbi scoring between input speech and HMM-based word model. Normalization technique of word likelihood for spontaneous speech recognition was also investigated.(3) Language model and task adaptationN-gram language models were constructed from EDR corpus, 5-million-word Japanese corpus. The models were investigated under various conditions about training text size, vocabulary and cutoff condition. The result of experiments clarified the optimum condition under a certain training text size. We carried out another experiments about task adaptation. An N-gram model from a dialog was mixed with the N-gram from EDR corpus, which made about 60% reduction of perplexity.

通过声学模型、词汇模型、语言模型等，将自发语音识别看作是一个考虑了各种限制条件的图搜索问题。为了在不降低识别性能的前提下减少识别处理的计算量，对自发语音识别的一些关键技术进行了研究。(1)声学模型和说话者自适应使用有限训练数据集的上下文相关声学建模的重要方面是如何绑定模型参数以及如何处理看不见的上下文。我们提出了基于决策树的连续状态分裂算法，并证明了该算法生成的HM-Net具有较高的准确率，能够表示任何上下文。研究了基于MAP估计方法的扬声器声学模型参数自适应问题。(2)快速匹配和似然归一化在大词汇量词识别中，研究了候选词的快速预选方法。对输入语音进行音位识别，并从输入语音中获得最优音位序列。为了选择候选词，采用最优音素序列进行DP匹配。通过输入语音和基于hmm的词模型之间的Viterbi评分对候选词进行验证。研究了用于自发语音识别的词似然归一化技术。(3)基于EDR语料库和500万字日语语料库构建了n- gram语言模型。在训练文本大小、词汇量和截止条件等条件下对模型进行了研究。实验结果明确了在一定训练文本大小下的最佳条件。我们进行了另一个关于任务适应的实验。将对话框的N-gram模型与EDR语料库的N-gram模型混合，使困惑率降低约60%。