In-Set/Out-of-Set Speaker Recognition Under Sparse Enrollment

• Published in: IEEE transactions on audio, speech, and language processing Vol. 15; no. 7; pp. 2044 - 2052
• Main Authors: Prakash, V.., Hansen, J.H.L.
• Format: Journal Article
• Language: English
• Published: IEEE 01.09.2007
• Subjects: Acoustic testing; Acoustics; Adaptation; Adaptation model; binary classification; cohort speakers; in-set/out-of-set; in-vehicle CU-move; limited training data; Loudspeakers; Natural language processing; NIST-SRE; Object recognition; Recognition; Robustness; score normalization; Speaker recognition; Speech; Speech analysis; Speech recognition; Streaming media; System performance; Training data
• ISSN: 1558-7916; 1558-7924
• DOI: 10.1109/TASL.2007.902058

In this paper, the problem of identifying in-set versus out-of-set speakers using extremely limited enrollment data is addressed. The recognition objective is to form a binary decision regarding an input speaker as being a legitimate member of a set of enrolled speakers or not. Here, the emphasis is on low enrollment (about 5 sec of speech for each enrolled speaker) and test data durations (2-8 sec), in a text-independent scenario. In order to overcome the limited enrollment, data from speakers that are acoustically close to a given in-set speaker are used to form an informative prior (base model) for speaker adaptation. Score normalization for in-set systems is addressed, and the difficulty of using conventional score normalization schemes for in-set speaker recognition is highlighted. Distribution scaling based score normalization techniques are developed specifically for the in-set/out-of-set problem and compared against existing score normalization schemes used in open-set speaker recognition. Experiments are performed using the following three separate corpora: (1) noise-free TIMIT; (2) noisy in-vehicle CU-move; and (3) the NIST-SRE-2006 database. Experimental results show a consistent increase in system performance for the proposed techniques.