Automatic recognition of prosodic phrases

Automatic recognition of prosodic phrases
复制标题

自动识别韵律短语

DOI：
--
复制
发表时间：
1991
期刊：
IEEE International Conference on Acoustics, Speech, and Signal Processing
影响因子：
--
通讯作者：
Mari Ostendorf
Mari Ostendorf
中科院分区：
--
文献类型：
--
作者：
Colin W. Wightman;Mari Ostendorf

文献摘要

被引文献

相似文献

作者报告的两个算法的发展，自动检测韵律短语。第一种算法使用简单的基于帧的似然分类器来检测呼吸和沉默，这产生了很大比例的主要短语中断。要标记其他层次的韵律结构，第二个算法，使用音素持续时间的语音识别器结合树量化器和隐马尔可夫模型来标记韵律短语休息的层次结构。第二种算法产生的短语中断预测与手部标签具有良好的相关性，并正确检测90%以上的主要短语边界。&lt;<ETX>&gt;
The authors report on the development of two algorithms to automatically detect prosodic phrases. The first algorithm uses simple frame-based likelihood classifiers to detect breaths and silences, which yields a large percentage of major phrase breaks. To label other levels of prosodic structure, a second algorithm is introduced that uses phoneme durations given by a speech recognizer in conjunction with a tree quantizer and hidden Markov model to label a hierarchy of prosodic phrase breaks. This second algorithm yields phrase break predictions that have good correlation with hand labels, and correctly detects more than 90% of the major phrase boundaries.<<ETX>>