Technical Program

SP-P12: Models for Speaker Recognition and Verification

Session Type: Poster
Time: Thursday, May 30, 08:00 - 10:00
Location: Poster Area D
Session Chair: Patrick Kenny, Centre de Recherche Informatique de Montréal
 
SP-P12.1: DIFFUSION MAPS FOR PLDA-BASED SPEAKER VERIFICATION
         Oren Barkan; Tel Aviv University / IBM Research - Haifa
         Hagai Aronowitz; IBM Haifa Research Labs
 
SP-P12.2: PROBABILISTIC LINEAR DISCRIMINANT ANALYSIS OF I-VECTOR POSTERIOR DISTRIBUTIONS
         Sandro Cumani; Brno University of Technology
         Oldrich Plchot; Brno University of Technology
         Pietro Laface; Politecnico di Torino
 
SP-P12.3: PLDA FOR SPEAKER VERIFICATION WITH UTTERANCES OF ARBITRARY DURATION
         Patrick Kenny; CRIM
         Themos Stafylakis; CRIM
         Pierre Ouellet; CRIM
         Md Jahangir Alam; Centre de Recherche Informatique de Montréal (CRIM)
         Pierre Dumouchel; CRIM
 
SP-P12.4: LATTICE MLLR BASED M-VECTOR SYSTEM FOR SPEAKER VERIFICATION
         Achintya Kumar Sarkar; Université Paris-Sud (XI)
         Claude Barras; Université Paris-Sud (XI)
         Viet Bac Le; Parc Orsay Universit´e
 
SP-P12.5: DISCRIMINATIVELY TRAINED BAYESIAN SPEAKER COMPARISON OF I-VECTORS
         Bengt Borgstrom; Massachusetts Institute of Technology, Lincoln Laboratory
         Alan McCree; Johns Hopkins University
 
SP-P12.6: DURATION MISMATCH COMPENSATION FOR I-VECTOR BASED SPEAKER RECOGNITION SYSTEMS
         Taufiq Hasan; The University of Texas at Dallas
         Rahim Saeidi; Radboud University Nijmegen
         John H.L. Hansen; The University of Texas at Dallas
         David Van Leeuwen; Radboud University Nijmegen
 
SP-P12.7: THE IITG SPEAKER VERIFICATION SYSTEMS FOR NIST SRE 2012
         Haris B C; Indian Institute of Technology Guwahati
         Gayadhar Pradhan; Indian Institute of Technology Guwahati
         Rohit Sinha; Indian Institute of Technology Guwahati
         S R Mahadeva Prasanna; Indian Institute of Technology Guwahati
 
SP-P12.8: PHONETICALLY-CONSTRAINED PLDA MODELING FOR TEXT-DEPENDENT SPEAKER VERIFICATION WITH MULTIPLE SHORT UTTERANCES
         Anthony Larcher; Institute for Infocomm Research
         Kong Aik Lee; Institute for Infocomm Research
         Bin Ma; Institute for Infocomm Research
         Haizhou Li; Institute for Infocomm Research
 
SP-P12.9: AN EFFICIENT IMPLEMENTATION OF PROBABILISTIC LINEAR DISCRIMINANT ANALYSIS
         Lukas Machlica; University of West Bohemia
         Zbynek Zajic; University of West Bohemia
 
SP-P12.10: A STUDY ON GMM-SVM WITH ADAPTIVE RELEVANCE FACTOR AND ITS COMPARISON WITH I-VECTOR AND JFA FOR SPEAKER RECOGNITION
         Changhuai You; Institute for Infocomm Research
         Haizhou Li; Institute for Infocomm Research
         Bin Ma; Institute for Infocomm Research
         Kong Aik Lee; Institute for Infocomm Research
 
SP-P12.11: ANTI-MODEL KL-SVM-NAP SYSTEM FOR NIST SRE 2012 EVALUATION
         Hanwu Sun; Institute for Infocomm Research
         Kong Aik Lee; Institute for Infocomm Research
         Bin Ma; Institute for Infocomm Research
 
SP-P12.12: SUPERVECTOR BAYESIAN SPEAKER COMPARISON
         Bengt Borgstrom; Massachusetts Institute of Technology, Lincoln Laboratory
         Alan McCree; Johns Hopkins University
 
SP-P12.13: UNIFYING PLDA AND POLYNOMIAL KERNEL SVMS
         Sibel Yaman; IBM T.J. Watson Research Center
         Jason Pelecanos; IBM T.J. Watson Research Center
         Weizhong Zhu; IBM T.J. Watson Research Center
 
SP-P12.14: LIKELIHOOD-RATIO EMPIRICAL KERNELS FOR I-VECTOR BASED PLDA-SVM SCORING
         Man-Wai Mak; The Hong Kong Polytechnic University
         Wei Rao; The Hong Kong Polytechnic University