The technologies of small or medium vocabulary speech recognition, such as voice command recognition, keyword spotting and continuous digit string speech recognition, are of great importance in the application-oriented study of speech recognition. 以命令词识别、关键词识别和连续数字串识别为代表的中小词汇量语音识别技术,是语音识别实用化研究中相当重要的方向。
The speech recognition technology of HMM is the technology that is based on the recognition system of the auto-construction probability provided by the practical digit. It is mainly used in speech recognition of a large number of vocabularies with the fine property of recognition and anti-noise. 隐马尔可夫模型(HMM)语音识别技术是一种基于训练数据提供的概率自动构造识别系统的技术,主要用于大量词汇的语音识别,而且具有良好的识别性能和抗噪性能。
The VQ HMM is described, and its speech recognition performance is compared with the conventional HMMs through the experiments on speaker independent Chinese spoken digit recognition. 介绍了VQHMM,并通过非特定人汉语数码语音识别实验对其识别性能与传统的HMM作了相应的比较。
At last, the thesis establishes Mandarin Digit Speech Recognition Simulation System ( MDSRSS) and Connected Mandarin Digit Speech Training System ( CMDSTS) separately; 最后,分别建立了数码语音识别仿真系统和连接数码语音训练系统。
The study of real time speech recognition to speaker independent Chinese digit 不定人汉语数字音实时识别方法的研究