| 摘要: |
| 文章研究并实现了汉语连续语音中的音节自动切分算法——基于归并的音节切分自动机(merging-based syllable detection automaton,简称MBSDA)算法.MBSDA算法利用了包括语音的短时能量、过零率和基音周期在内的多种特征参数,把特征参数高度相似的相邻帧(1帧或若干帧)的语音信号进行“归并(merging)”,形成“归并类似段(merged similar segment,简称MSS)”,它们被认定属于同一音节的相同状态.这些MSS经过一个包含若干状态的“音节切分自动机( |
| 关键词: 音节切分,归并,音节切分自动机、韵母特征类段,音节个数范围. |
| DOI： |
| 分类号: |
| 基金项目: |
|
| Merging-based Syllable Detection Automaton in Continuous Chinese Speech Recognition |
|
ZHANG Ji-yong,ZHENG Fang,DU Shu,SONG Zhan-jiang,XU Ming-xing
|
| Abstract: |
| In this paper, an automatic syllable detection method namely merging-based syllable detection automaton (MBSDA) is studied and implemented. The MBSDA uses a variety of features including the frame energy, the zero crossing rate and the fundamental frequency to merge similar consecutive frames (one or several frames) into one merged similar segment (MSS). The frames in the same MSS are treated as frames of the same state of a phonetic. These MSSs are passed into a syllable detection automaton (SDA) to give the syllable detection results. In addition, the MBSDA gives the range of syllable number (RNS) of each definite detection segment. |
| Key words: Syllable detection, merging, syllable detection automaton, vowel feature segment, range of syllable number. |
