Publication Details
Factorization of Discriminatively Trained i-Vector Extractor for Speaker Recognition
Plchot Oldřich, Ing., Ph.D. (DCGM)
Glembek Ondřej, Ing., Ph.D.
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
SRE
In this work, we continue in our research on i-vector extractor for speaker
verification (SV) and we optimize its architecture for fast and effective
discriminative training. We were motivated by computational and memory
requirements caused by the large number of parameters of the original generative
ivector model. Our aim is to preserve the power of the original generative model,
and at the same time focus the model towards extraction of speaker-related
information. We show that it is possible to represent a standard generative
i-vector extractor by a model with significantly less parameters and obtain
similar performance on SV tasks. We can further refine this compact model by
discriminative training and obtain i-vectors that lead to better performance on
various SV benchmarks representing different acoustic domains.
@inproceedings{BUT159998,
author="Ondřej {Novotný} and Oldřich {Plchot} and Ondřej {Glembek} and Lukáš {Burget}",
title="Factorization of Discriminatively Trained i-Vector Extractor for Speaker Recognition",
booktitle="Proceedings of Interspeech",
year="2019",
journal="Proceedings of Interspeech",
volume="2019",
number="9",
pages="4330--4334",
publisher="International Speech Communication Association",
address="Graz",
doi="10.21437/Interspeech.2019-1757",
issn="1990-9772",
url="https://www.isca-speech.org/archive/Interspeech_2019/pdfs/1757.pdf"
}