13 years of speaker recognition research at BUT, with longitudinal analysis of NIST SRE. (September 2020)

• Record Type: Journal Article
• Authors: Matějka, Pavel; Plchot, Oldřich; Glembek, Ondřej; Burget, Lukáš; Rohdin, Johan; Zeinali, Hossein; Mošner, Ladislav; Silnova, Anna; Novotný, Ondřej; Diez, Mireia; "Honza" Černocký, Jan
• Is Part Of: Computer speech & language. Volume 63(2020)
• Publication Date: 2020-09
• Subjects: Speaker recognition -- NIST -- Evaluations -- GMM -- Eigen-channel compensation -- JFA -- I-vectors -- DNN Embedding -- X-vectors; 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.2019.101035
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: 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. Abstract: In this paper, we present a brief history and a "longitudinal study" of all important milestone modelling techniques used in text independent speaker recognition since Brno University of Technology (BUT) first participated in the NIST Speaker Recognition Evaluation (SRE) in 2006—GMM MAP, GMM MAP with eigen-channel adaptation, Joint Factor Analysis, i-vector and DNN embedding (x-vector). To emphasize the historical context, the techniques are evaluated on all NIST SRE sets since 2004 on a time-machine principle, i.e. a system is always trained using all data available up till the year of evaluation. Moreover, as user-contributed audiovisual content dominates nowadays' Internet, we representatively include the Speakers In The Wild (SITW) and VOiCES challenge datasets in the evaluation of our systems. Not only we present a comparison of the modelling techniques, but we also show the effect of sampling frequency.