Text independent voiceprint recognition model based on I-vector

Abstract

Speaker Recognition is a technology for identifying people based on the Voiceprint characteristics contained in voice, and is a kind of biometric authentication technology. According to different recognition methods, Voiceprint recognition can be divided into three categories [1]. (1) Speaker discrimination is to distinguish who is talking from a given speaker set; (2) speaker confirmation is to judge whether someone is speaking or not; (3) speaker segmenting and clustering is to distinguish the switching time of different speakers based on the voice formed by multiple speakers.