David A. van Leeuwen

David A. van Leeuwen

Auto-generated profile, based on publicly available information

David A. van Leeuwen

CLST/CLS Radboud University Nijmegen The Netherlands

Research Focus & Metrics

Academic Career Length

36Years (1991-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 August 2013 in IEEE Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
MMMiranti Indar Mandasari
Miranti Indar Mandasari
RSRahim Saeidi
Rahim Saeidi
MMMitchell McLaren
Mitchell McLaren
DLDavid A. van Leeuwen
David A. van Leeuwen
This paper investigates the effect of utterance duration to the calibration of a modern i-vector speaker recognition system with probabilistic linear discriminant analysis (PLDA) modeling. A calibration approach to deal with these effects using quality measure functions (QMFs) is proposed to include duration in the calibration transformation. Extensive experiments are performed in order to evaluate the robustness of the proposed calibration approach for unseen conditions in the training of calibration parameters. Using the latest NIST corpora for evaluation, results highlight the importance of considering the quality metrics like duration in calibrating the scores for automatic speaker recognition systems.

1 November 2012 in Speech Communication
Verified
Journal Article
Closed access
KTKhiet P. Truong
Khiet P. Truong
DLDavid A. van Leeuwen
David A. van Leeuwen
FJFranciska M.G. de Jong
Franciska M.G. de Jong

25 July 2011 in IEEE Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Open access
MHMarijn Huijbregts
Marijn Huijbregts
DLDavid A. van Leeuwen
David A. van Leeuwen
Performing speaker diarization of very long recordings is a problem for most diarization systems that are based on agglomerative clustering with an hidden Markov model (HMM) topology. Performing collection-wide speaker diarization, where each speaker is identified uniquely across the entire collection, is even a more challenging task. In this paper we propose a method with which it is possible to efficiently perform diarization of long recordings. We have also applied this method successfully to a collection of a total duration of approximately 15 hours. The method consists of first segmenting long recordings into smaller chunks on which diarization is performed. Next, a speaker detection system is used to link the speech clusters from each chunk and to assign a unique label to each speaker in the long recording or in the small collection. We show for three different audio collections that it is possible to perform high-quality diarization with this approach. The long meetings from the ICSI corpus are processed 5.5 times faster than the originally needed time and by uniquely labeling each speaker across the entire collection it becomes possible to perform speaker-based information retrieval with high accuracy (mean average precision of 0.57).

1 December 2018 in Speech Communication
Verified
Journal Article
Closed access
EYEmre Yılmaz
Emre Yılmaz
MMMitchell McLaren
Mitchell McLaren
HHHenk van Den Heuvel
Henk van Den Heuvel
DLDavid A. van Leeuwen
David A. van Leeuwen

6 September 2009
Verified
Conference Paper
Open access
KTKhiet P. Truong
Khiet P. Truong
DLDavid A. van Leeuwen
David A. van Leeuwen
MNMark Neerincx
Mark Neerincx
FJFranciska M. G. de Jong
Franciska M. G. de Jong

6 September 2009
Verified
Conference Paper
Open access
DLDavid A. van Leeuwen
David A. van Leeuwen
JKJudith Kessens
Judith Kessens
ESEric Sanders
Eric Sanders
HHHenk van Den Heuvel
Henk van Den Heuvel