13 years of speaker recognition research at BUT, with longitudinal analysis of NIST SRE
Computer Speech & Language(2020)
摘要
•We present a “longitudinal study” of all important milestone techniques used in speaker recognition by evaluating on multiple NIST SREs.•We provide aa analysis of difficulty of individual NIST SREs.•We investigate the impact of the amount of training data on performance of particular Speaker Recognition methods.•We evaluate milestone techniques also on the Speakers In The Wild (SITW) and VOiCES challenge datasets, as the amount of- and interest in user-contributed audiovisual content grows.
更多查看译文
关键词
Speaker recognition,NIST,Evaluations,GMM,Eigen-channel compensation,JFA,I-vectors,DNN Embedding,X-vectors
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要