Publication Details
Recent Progress in Prosodic Speaker Verification
Ferrer Luciana (SRI)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Shriberg Elisabeth (SRI)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
Prosodic speaker verification, SNERFs, MSM, iVector, PLDA
We have proposed a technique for modeling complex prosodic features, such as SNERFs, using a multinomial subspace model for feature extraction and probabilistic linear discriminant analysis for session variability compensation.
We describe recent progress in the field of prosodic modeling for speaker verification. In a previous paper, we proposed a technique for modeling syllable-based prosodic features that uses a multinomial subspace model for feature extraction and within-class covariance normalization or linear discriminant analysis for session variability compensation. In this paper, we show that performance can be significantly improved with the use of probabilistic linear discriminant analysis (PLDA) for session variability compensation. This system does not require score normalization. We report an equal error rate below 7% on a NIST 2008 task. To our knowledge, this is the best reported result to date for a prosodic system for speaker recognition. Fusion of this system with a state-of-the-art acoustic baseline system yields 10% relative improvement in the new detection cost function (DCF) as defined by NIST.
@INPROCEEDINGS{FITPUB9656,
author = "Marcel Kockmann and Luciana Ferrer and Luk\'{a}\v{s} Burget and Elisabeth Shriberg and Jan \v{C}ernock\'{y}",
title = "Recent Progress in Prosodic Speaker Verification",
pages = "4556--4559",
booktitle = "Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011",
year = 2011,
location = "Praha, CZ",
publisher = "IEEE Signal Processing Society",
ISBN = "978-1-4577-0537-3",
language = "english",
url = "https://www.fit.vut.cz/research/publication/9656"
}