Please use this identifier to cite or link to this item:
Title: Boosting the performance of I-vector based speaker verification via utterance partitioning
Authors: Rao, W
Mak, MW 
Keywords: I-vectors
linear discriminant analysis
speaker verification
support vector machines
utterance partitioning with acoustic vector resampling (UP-AVR)
Issue Date: 2013
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on audio, speech and language processing, 2013, v. 21, no. 5, 6423258, p. 1012-1022 How to cite?
Journal: IEEE transactions on audio, speech and language processing 
Abstract: The success of the recent i-vector approach to speaker verification relies on the capability of i-vectors to capture speaker characteristics and the subsequent channel compensation methods to suppress channel variability. Typically, given an utterance, an i-vector is determined from the utterance regardless of its length. This paper investigates how the utterance length affects the discriminative power of i-vectors and demonstrates that the discriminative power of i-vectors reaches a plateau quickly when the utterance length increases. This observation suggests that it is possible to make the best use of a long conversation by partitioning it into a number of sub-utterances so that more i-vectors can be produced for each conversation. To increase the number of sub-utterances without scarifying the representation power of the corresponding i-vectors, repeated applications of frame-index randomization and utterance partitioning are performed. Results on NIST 2010 speaker recognition evaluation (SRE) suggest that (1) using more i-vectors per conversation can help to find more robust linear discriminant analysis (LDA) and within-class covariance normalization (WCCN) transformation matrices, especially when the number of conversations per training speaker is limited; and (2) increasing the number of i-vectors per target speaker helps the i-vector based support vector machines (SVM) to find better decision boundaries, thus making SVM scoring outperforms cosine distance scoring by 19% and 9% in terms of minimum normalized DCF and EER.
ISSN: 1558-7916
EISSN: 1558-7924
DOI: 10.1109/TASL.2013.2243436
Appears in Collections:Journal/Magazine Article

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Feb 22, 2019


Last Week
Last month
Citations as of Feb 23, 2019

Page view(s)

Last Week
Last month
Citations as of Feb 17, 2019

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.