• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>European Conference on Speech Communication and Technology - EUROSPEECH 2003(INTERSPEECH 2003) vol.4; 20030901-04; Geneva(CH) >NOISE ROBUSTNESS IN SPEECH TO SPEECH TRANSLATION
【24h】

NOISE ROBUSTNESS IN SPEECH TO SPEECH TRANSLATION

机译：语音到语音翻译的鲁棒性

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

This paper describes various noise robustness issues in a speech-to-speech translation system. We present quantitative measures for noise robustness in the context of speech recognition accuracy and speech-to-speech translation performance. To enhance noise immunity, we explore two approaches to improve the overall speech-to-speech translation performance. First, a multi-style training technique is used to tackle the issue of environmental degradation at the acoustic model level. Second, a pre-processing technique, CDCN, is exploited to compensate for the acoustic distortion at the signal level. Further improvement can be obtained by combining both schemes. In addition to recognition accuracy for speech recognition, this paper studies and examines how closely speech recognition accuracy is related the overall speech-to-speech recognition. When we apply the proposed schemes to an English-to-Chinese translation task, the word error rate for our speech recognition subsystem is substantially reduced by 28% relative, to 13.2% from 18.9% for test data of 15dB SNR. The corresponding BLEU score improves to 0.478 from 0.43 for the overall speech-to-speech translation. Similar improvements are also observed for a lower SNR condition.
机译：本文介绍了语音到语音翻译系统中的各种噪声鲁棒性问题。我们在语音识别准确性和语音到语音翻译性能的背景下提出了针对噪声鲁棒性的定量措施。为了增强抗噪能力，我们探索了两种方法来改善整体语音到语音的翻译性能。首先，采用多种样式的训练技术来解决声学模型级别的环境退化问题。其次，采用了一种预处理技术CDCN来补偿信号级的声音失真。通过将两种方案结合起来，可以获得进一步的改进。除了用于语音识别的识别准确度之外，本文还研究并检验了语音识别准确度与整体语音到语音识别之间的紧密关系。当我们将拟议的方案应用于英语到中文的翻译任务时，语音识别子系统的单词错误率相对降低了28％，从15dB SNR的测试数据的18.9％降低到13.2％。整体语音转语音的BLEU分数从0.43提高到0.478。对于较低的SNR条件，也观察到了类似的改进。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号