Robust discriminative training against data insufficiency in PLDA-based speaker verification. (January 2016)

• Record Type: Journal Article
• Authors: Rohdin, Johan; Biswas, Sangeeta; Shinoda, Koichi
• Is Part Of: Computer speech & language. Volume 35(2016)
• Page Start: 32
• Page End: 57
• Publication Date: 2016-01
• Subjects: Speaker verification -- PLDA -- Discriminative training -- Statistically dependent training data -- Overfitting; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2015.06.003
• Languages: English
• ISSNs: 0885-2308

Abstract

Abstract : Highlights: We address data insufficiency in discriminative PLDA training. First, we compensate for statistical dependencies in the training data. Second, we propose three constrained discriminative training schemes. Abstract: Probabilistic linear discriminant analysis (PLDA) with i-vectors as features has become one of the state-of-the-art methods in speaker verification. Discriminative training (DT) has proven to be effective for improving PLDA's performance but suffers more from data insufficiency than generative training (GT). In this paper, we achieve robustness against data insufficiency in DT in two ways. First, we compensate for statistical dependencies in the training data by adjusting the weights of the training trials in order for the training loss to be an accurate estimate of the expected loss. Second, we propose three constrained DT schemes, among which the best was a discriminatively trained transformation of the PLDA score function having four parameters. Experiments on the male telephone part of the NIST SRE 2010 confirmed the effectiveness of our proposed techniques. For various number of training speakers, the combination of weight-adjustment and the constrained DT scheme gave between 7% and 19% relative improvements in C ˆ llr over GT followed by score calibration. Compared to another baseline, DT of all the parameters of the PLDA score function, the improvements were larger.