• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>6th International Workshop on Computational Processing of the Portuguese Language PROPOR 2003 Jun 26-27, 2003 Faro, Portugal >Improving the Accuracy of the Speech Synthesis Based Phonetic Alignment Using Multiple Acoustic Features
【24h】

Improving the Accuracy of the Speech Synthesis Based Phonetic Alignment Using Multiple Acoustic Features

机译：使用多个声学特征提高基于语音合成的语音对齐的准确性

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

The phonetic alignment of the spoken utterances for speech research are commonly performed by HMM-based speech recognizers, in forced alignment mode, but the training of the phonetic segment models requires considerable amounts of annotated data. When no such material is available, a possible solution is to synthesize the same phonetic sequence and align the resulting speech signal with the spoken utterances. However, without a careful choice of acoustic features used in this procedure, it can perform poorly when applied to continuous speech utterances. In this paper we propose a new method to select the best features to use in the alignment procedure for each pair of phonetic segment classes. The results show that this selection considerably reduces the segment boundary location errors.
机译：用于语音研究的话语的语音对齐通常由基于HMM的语音识别器以强制对齐模式执行，但是语音段模型的训练需要大量注释数据。当没有此类材料可用时，一种可能的解决方案是合成相同的语音序列，并将结果语音信号与口头发音对齐。但是，如果不仔细选择此过程中使用的声学功能，则在应用于连续语音时，其性能可能会很差。在本文中，我们提出了一种新方法，用于为每对语音段类别选择在对齐过程中使用的最佳功能。结果表明，该选择大大减少了段边界位置误差。

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