Non-uniform unit parsing for SSS-LR continuous speech recognition

Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing Pub Date : 1994-04-19 DOI:10.1109/ICASSP.1994.389697

H. Singer, J. Takami, S. Matsunaga

引用次数: 3

Abstract

We describe recent improvements in ATR's experimental speech recognition system ATREUS, which serves as a recognition font end for the speech translation system ASURA. Our next goal is spontaneous speech translation. To constrain the potentially huge search space, better prosodic control, better probabilistic language models and better acoustic models are proposed. The SSS-LR parser was modified to work with non-uniform unit type acoustic and duration models. Experimental results showed, that, for example, use of mora trigram probabilities improved the phrase error rate from 17% to 14%.<>

查看原文本刊更多论文

ss - lr连续语音识别的非统一单元解析

我们描述了ATR的实验性语音识别系统ATREUS的最新改进，该系统作为语音翻译系统ASURA的识别字体端。我们的下一个目标是自发语音翻译。为了限制潜在的巨大搜索空间，提出了更好的韵律控制、更好的概率语言模型和更好的声学模型。对ssss - lr解析器进行了修改，使其能够处理非均匀单元型声学和持续时间模型。实验结果表明，例如，使用mora三组概率将短语错误率从17%提高到14%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing

自引率

0.00%

发文量