首页>
外国专利>
Method and system for creating speaker recognition data, and method and system for speaker recognition
Method and system for creating speaker recognition data, and method and system for speaker recognition
展开▼
机译:用于创建说话人识别数据的方法和系统以及用于说话人识别的方法和系统
展开▼
页面导航
摘要
著录项
相似文献
摘要
Disclosed is a voice registration method for voice recognition, comprising the steps of analyzing a spectrum of a sound signal inputted from the outside; extracting predetermined language units for a speaker recognition from a voice signal in the sound signal; measuring the loudness of each language unit; collecting voice data on registered (background) speakers including loudness data of the plurality of background speakers as a reference onto voice database; determining whether the loudness of each language unit is within a predetermined loudness range based on the voice data base; learning each language unit by using a multi-layer perceptron in the case that at least a predetermined number of language units are within the predetermined loudness range; and storing data on the learned language unit as data for recognizing the speaker. With this configuration, loudness of a speaker is considered at learning for registering his/her voice and at verifying a speaker.
展开▼