MFCC is the main parameter for speech recognition.
MFCC是语音识别的重要参数。
参考来源 - 音频信息隐藏关键技术研究及识别技术的信息安全应用Through the discussion of vector quantization parameter’s choice, the result that for medium vocabulary speech recognition, the codebook capacity should be 64 or 128 is made.
通过矢量量化参数选取的讨论,得到对于中等词汇量的语言识别,矢量量化的码本大小应为64或128的结论。
参考来源 - 基于隐马尔可夫模型的语音识别方法的研究Speech recognition system is the most complex among all the biological statistic systems.
在所有的生物统计学系统中，语音识别最复杂，而且精确度最低。
参考来源 - 声纹分析的非线性动力学方法研究·2,447,543篇论文数据，部分数据来源于NoteExpress
N the understanding of continuous speech by a computer 电脑对无中断语言的识别
Speech-recognition technology, which permits automated responses to telephone calls, is also faring well.
可以自动回复来电的语音识别技术也正在取得成功。
Speech recognition software is also helpful to deaf people.
语音识别软件对聋人也很有帮助。
Some speech recognition software can even hear words spoken in one language and then translate them into another language.
一些语音识别软件甚至可以识别一种语言的话语，并将其翻译成另一种语言。
应用推荐