Publication detail

Analysis Of DNN Approaches To Speaker Identification

MATĚJKA, P. GLEMBEK, O. NOVOTNÝ, O. PLCHOT, O. GRÉZL, F. BURGET, L. ČERNOCKÝ, J.

Original Title

Analysis Of DNN Approaches To Speaker Identification

Type

conference paper

Language

English

Original Abstract

This work studies the usage of the Deep Neural Network (DNN) Bottleneck (BN) features together with the traditional MFCC features in the task of i-vector-based speaker recognition. We decouple the sufficient statistics extraction by using separate GMM models for frame alignment, and for statistics normalization and we analyze the usage of BN and MFCC features (and their concatenation) in the two stages. We also show the effect of using full-covariance GMM models, and, as a contrast, we compare the result to the recent DNN-alignment approach. On the NIST SRE2010, telephone condition, we show 60% relative gain over the traditional MFCC baseline for EER (and similar for the NIST DCF metrics), resulting in 0.94% EER.

Keywords

automatic speaker identification, deep neural networks, bottleneck features, i-vector

Authors

MATĚJKA, P.; GLEMBEK, O.; NOVOTNÝ, O.; PLCHOT, O.; GRÉZL, F.; BURGET, L.; ČERNOCKÝ, J.

Released

20. 3. 2016

Publisher

IEEE Signal Processing Society

Location

Shanghai

ISBN

978-1-4799-9988-0

Book

Proceedings of the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016

Pages from

5100

Pages to

5104

Pages count

5

URL

BibTex

@inproceedings{BUT130927,
  author="Pavel {Matějka} and Ondřej {Glembek} and Ondřej {Novotný} and Oldřich {Plchot} and František {Grézl} and Lukáš {Burget} and Jan {Černocký}",
  title="Analysis Of DNN Approaches To Speaker Identification",
  booktitle="Proceedings of the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016",
  year="2016",
  pages="5100--5104",
  publisher="IEEE Signal Processing Society",
  address="Shanghai",
  doi="10.1109/ICASSP.2016.7472649",
  isbn="978-1-4799-9988-0",
  url="https://www.fit.vut.cz/research/publication/11140/"
}