Advanced computational models and learning theories for spoken language processing
Advanced computational models and learning theories for spoken language processing
复制标题
DOI：
10.1109/mci.2006.1626489
复制
发表时间：
2006-05-01
影响因子：
9
通讯作者：
Katagiri, Shigeru
中科院分区：
文献类型：
--
作者：
Nakamura, Atsushi;Watanabe, Shinji;Katagiri, Shigeru
人形机器人和交互代理研究的最新进展凸显了自动语音识别（ASR）作为赋予此类代理通过语音进行通信的能力的手段的重要性和期望。本文介绍了 NTT 通信科学实验室 (NTT-CSL) 为应对 ASR 中的此类挑战而采取的一些方法。我们特别关注通过有限状态机进行快速搜索的方法、用于语音建模和分类的贝叶斯解决方案，以及用于最小化大词汇量连续语音识别中的错误的判别训练方法
Recent developments in research on humanoid robots and interactive agents have highlighted the importance of and expectation on automatic speech recognition (ASR) as a means of endowing such an agent with the ability to communicate via speech. This article describes some of the approaches pursued at NTT Communication Science Laboratories (NTT-CSL) for dealing with such challenges in ASR. In particular, we focus on methods for fast search through finite-state machines, Bayesian solutions for modeling and classification of speech, and a discriminative training approach for minimizing errors in large vocabulary continuous speech recognition