Speaker feature modeling utilizing constrained maximum likelihood linear regression and Gaussian mixture models

• 主要作者: Magsino, Elmer R.
• 格式: text
• 出版: Animo Repository 2020
• 主題: Automatic speech recognition; Regression analysis; Electrical and Computer Engineering
• 在線閱讀: https://animorepository.dlsu.edu.ph/faculty_research/2974

This paper describes a speaker recognition system based on feature extraction utilizing the constrained maximum likelihood linear regression (CMLLR) speaker adaptation, while using Gaussian mixture models (GMM) to model the speaker and background models. For the input acoustic signals, the cepstral...