Research on Speaker Recognition Technology Based on Feature Model

Speaker recognition, also known as voiceprint recognition, as the name implies, is to identify "who is speaking" by sound, and is a biometric identification technology that identifies the speaker's identity based on the speaker's personality information in the voice signal. In this paper, through a survey of speaker recognition literature and related technologies, the two main tasks of speaker recognition, speaker confirmation and speaker recognition, are introduced, and some models in the development of speaker recognition technology are introduced. From the early Gaussian Mixture Model-Universal Background Model, to Joint Factor Analysis and I-vector model, to the emergence of various new feature models combined with deep learning, the recognition effect is getting better and better. Recognizable scenarios are also becoming more complex. Finally, the speaker recognition technology is summarized and its future research is prospected.