Minimum Bayes Risk Estimation and Decoding in Large Vocabulary Continuous Speech Recognition

William BYRNE

首页> 外文期刊>IEICE Transactions on Information and Systems >Minimum Bayes Risk Estimation and Decoding in Large Vocabulary Continuous Speech Recognition

【24h】

Minimum Bayes Risk Estimation and Decoding in Large Vocabulary Continuous Speech Recognition

机译：大词汇量连续语音识别中的最小贝叶斯风险估计和解码

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 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Minimum Bayes risk estimation and decoding strategies based on lattice segmentation techniques can be used to refine large vocabulary continuous speech recognition systems through the estimation of the parameters of the underlying hidden Markov models and through the identification of smaller recognition tasks which provides the opportunity to incorporate novel modeling and decoding procedures in LVCSR. These techniques are discussed in the context of going 'beyond HMMs', showing in particular that this process of subproblem identification makes it possible to train and apply small-domain binary pattern classifiers, such as Support Vector Machines, to large vocabulary continuous speech recognition.

机译：基于格点分割技术的最小贝叶斯风险估计和解码策略可用于通过估计潜在的隐马尔可夫模型的参数并通过识别较小的识别任务来细化大型词汇连续语音识别系统，从而为整合新颖的算法提供了机会LVCSR中的建模和解码过程。在“超越HMM”的背景下讨论了这些技术，尤其表明，该子问题识别过程使训练和应用小域二进制模式分类器（例如支持向量机）到大词汇量连续语音识别成为可能。

著录项

来源
《IEICE Transactions on Information and Systems》 |2006年第3期|p.900-907|共8页
作者
William BYRNE;
展开▼
作者单位

Cambridge University Engineering Department, Trumpington Street, Cambridge CB2 1PZ, U.K.;

展开▼
收录信息美国《科学引文索引》(SCI);美国《工程索引》(EI);
原文格式 PDF
正文语种 eng
中图分类无线电电子学、电信技术;
关键词
discriminative training; acoustic modeling; automatic speech recognition; maximum mutual information;

机译：判别训练;声学建模;语音自动识别;最大互信息;

相似文献

外文文献
中文文献
专利

1. MINIMUM BAYES RISK RETIMATION AND DECODING IN LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION [J] . William Byrne 電子情報通信学会技術研究報告. 音声. Speech . 2004,第541期

机译：大型词汇连续语音识别中的最小贝叶斯风险估计和解码
2. MINIMUM BAYES RISK RETIMATION AND DECODING IN LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION [J] . William Byrne 電子情報通信学会技術研究報告. 言語理解とコミュニケーション. Natural Language Understanding and Models of Communication . 2004,第538期

机译：大型词汇连续语音识别中的最小贝叶斯风险估计和解码
3. Lattice segmentation and minimum Bayes risk discriminative training for large vocabulary continuous speech recognition [J] . Vlasios Doumpiotis, William Byrne Speech Communication . 2006,第2期

机译：大词汇量连续语音识别的格划分和最小贝叶斯风险判别训练
4. Pinched Lattice Minimum Bayes Risk Discriminative Training for Large Vocabulary Continuous Speech Recognition [C] . Vlasios Doumpiotis, William Byrne International Conference on Spoken Language Processing; 20041004-08; Jeju(KR) . 2004

机译：大词汇量连续语音识别的收缩格最小贝叶斯风险判别训练
5. Discriminative training for speaker adaptation and minimum Bayes risk estimation in large vocabulary speech recognition. [D] . Doumpiotis, Vlasios. 2005

机译：大词汇量语音识别中的说话人适应性和最低贝叶斯风险估计的判别训练。
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. Minimum Bayes Risk Estimation and Decoding in Large Vocabulary Continuous Speech Recognition [O] . William Byrne 2003

机译：大词汇量连续语音识别中的最小贝叶斯风险估计和解码

Minimum Bayes Risk Estimation and Decoding in Large Vocabulary Continuous Speech Recognition

摘要

著录项

相似文献

相关主题

期刊订阅