首页> 外文会议>Chinese Spoken Language Processing; Lecture Notes in Artificial Intelligence; 4274 >All-Path Decoding Algorithm for Segmental Based Speech Recognition
【24h】

All-Path Decoding Algorithm for Segmental Based Speech Recognition

机译:基于分段的语音识别全路径解码算法

获取原文
获取原文并翻译 | 示例

摘要

In conventional speech processing, researchers adopt a dividable assumption, that the speech utterance can be divided into nonoverlapping feature sequences and each segment represents an acoustic event or a label. And the probability of a label sequence on an utterance approximates to the probability of the best utterance segmentation for this label sequence. But in the real case, feature sequences of acoustic events may be overlapped partially, especially for the neighboring phonemes within a syllable. And the best segmentation approximation even reinforces the distortion by the dividable assumption. In this paper, we propose an all-path decoding algorithm, which can fuse the information obtained by different segmentations (or paths) without paying obvious computation load, so the weakness of the dividable assumption could be alleviated. Our experiments show, the new decoding algorithm can improve the system performance effectively in tasks with heavy insertion and deletion errors.
机译:在常规语音处理中,研究人员采用可分割的假设,即语音发声可以分为不重叠的特征序列,每个片段代表一个声音事件或一个标签。标签序列在发声上的概率接近此标签序列的最佳发声分段的概率。但是在实际情况下,声音事件的特征序列可能会部分重叠,尤其是对于音节中的相邻音素而言。最佳分割逼近甚至可以通过可分割的假设增强失真。在本文中,我们提出了一种全路径解码算法,该算法可以融合由不同分段(或路径)获得的信息,而无需付出明显的计算负担,因此可以缓解可分假设的弱点。我们的实验表明,新的解码算法可以有效地解决具有严重插入和删除错误的任务中的系统性能。

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