Supervised domain adaptation for I-vector based speaker recognition

• Published in: Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 4047 - 4051
• Main Authors: Garcia-Romero, Daniel, McCree, Alan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2014
• Subjects: Adaptation models; Approximation methods; Bayes methods; Computational modeling; i-vectors; PLDA; Speaker recognition; Speech; supervised domain adaptation; Training

In this paper, we present a comprehensive study on supervised domain adaptation of PLDA based i-vector speaker recognition systems. After describing the system parameters subject to adaptation, we study the impact of their adaptation on recognition performance. Using the recently designed domain ada...