A New Dynamic HMM Model for Speech Recognition

机译：一种新的动态HMM语音识别模型

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

In this paper, we describe a new method to perform speech recognition based on Dynamic HMM architecture. Pitch values are treated as hidden layer and used to modify the parameters of observation probability functions. The results show that the new model achieves approximately 10 percent relative error reductions both in base-syllable recognition task and tonal syllable recognition task. The new method can be used compatibly with conventional HMM based EM training algorithm and Viterbi decoding algorithm.

机译：在本文中，我们描述了一种基于动态HMM架构进行语音识别的新方法。间距值被视为隐藏层，并用于修改观察概率函数的参数。结果表明，新模型在基本音节识别任务和音调音节识别任务中均实现了约10％的相对误差减少。该新方法可以与基于传统HMM的EM训练算法和Viterbi解码算法兼容。

著录项

来源
《European Conference on Speech Communication and Technology v.4; 20010903-20010907; Aalborg; DK》|2001年|P.2769-2772|共4页
会议地点 Aalborg(DK);Aalborg(DK)
作者
Feili Chen; Eric Chang;
展开▼
作者单位

Shanghai JiaoTong University and Bell-lab Joint Lab Department of Electronic Engineering, SJTU 5F, 49 Zhichun Road, Haidian District, Beijing, China;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类传播理论;
关键词

相似文献

外文文献
中文文献
专利

1. Dynamic HMM Model with Estimated Dynamic Property in Continuous Mandarin Speech Recognition [J] . CHENFeili, ZHUJie 电子学报：英文版 . 2003,第002期

机译：连续汉语语音识别中具有估计动态特性的动态HMM模型
2. HMM-based stressed speech modeling with application to improved synthesis and recognition of isolated speech under stress [J] . Bou-Ghazale S.E., Hansen J.H.L. IEEE Transactions on Speech and Audio Proceeding . 1998,第3期

机译：基于HMM的压力语音建模及其在压力下孤立语音的合成和识别中的应用
3. HMM-based stressed speech modeling with application to improvedsynthesis and recognition of isolated speech under stress [J] . Bou-Ghazale S.E., Hansen J.H.L. IEEE Transactions on Speech and Audio Proceessing . 1998,第3期

机译：基于HMM的压力语音建模及其在压力下孤立语音的合成和识别中的应用
4. Maximum Relative Margin Estimation of HMMs Based on N-Best String Models for Continuous Speech Recognition [C] . Chaojun Liu, Hui Jiang, Rigazio, . 2005

机译：基于N-Best字符串模型的HMM的最大相对余量估计
5. Modeling articulatory dynamics using HMM techniques for automatic speech recognition. [D] . Erler, Kevin J. 1994

机译：使用HMM技术对发音动力学进行建模以实现自动语音识别。
6. Estimation of Phoneme-Specific HMM Topologies for the Automatic Recognition of Dysarthric Speech [O] . Santiago-Omar Caballero-Morales 2013

机译：语音异常自动识别的音素特定HMM拓扑估计
7. Connected phoneme HMMs with implicit duration modelling for better speech recognition [O] . Ramachandrula Sitaram, Thippur Sreenivas 1997

机译：具有隐式持续时间建模的连接音素HMM，可实现更好的语音识别

A New Dynamic HMM Model for Speech Recognition

摘要

著录项

相似文献

相关主题

期刊订阅