Syllable segmentation in continuous speech is very difficult.
连续语流中的音节分割是非常困难的。
参考来源 - 基于音节的汉语连续语音声调识别方法研究·2,447,543篇论文数据，部分数据来源于NoteExpress
本文提出一种汉语语音连接词音节分割方法。
This paper presented a syllable segmentation method for Chinese connected speech.
实验验证表明，本文的分段方法对连续汉语语音的音节分割是有效的。
Experimental verification shows that the method of segmentation is effective in isolating the syllables in continuous Chinese speech.
并由实验证明，MFDS算法使准连续语音音节分割正确率达到98%以上。
The experiments show that the correct rate of separating for continuous speech by MFDS is above 98%.
应用推荐