Detail publikace

Recent Progress in Prosodic Speaker Verification

Originální název

Recent Progress in Prosodic Speaker Verification

Anglický název

Recent Progress in Prosodic Speaker Verification

Jazyk

en

Originální abstrakt

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.

Anglický abstrakt

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.

BibTex


@inproceedings{BUT76386,
  author="Marcel {Kockmann} and Luciana {Ferrer} and Lukáš {Burget} and Elisabeth {Shriberg} and Jan {Černocký}",
  title="Recent Progress in Prosodic Speaker Verification",
  annote="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.",
  address="IEEE Signal Processing Society",
  booktitle="Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011",
  chapter="76386",
  edition="NEUVEDEN",
  howpublished="print",
  institution="IEEE Signal Processing Society",
  year="2011",
  month="may",
  pages="4556--4559",
  publisher="IEEE Signal Processing Society",
  type="conference paper"
}