Publication Details
On the Usage of Phonetic Information for Text-independent Speaker Embedding Extraction
Rohdin Johan Andréas, M.Sc., Ph.D. (DCGM)
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Plchot Oldřich, Ing., Ph.D. (DCGM)
Qian Yanmin
YU, K.
Černocký Jan, prof. Dr. Ing. (DCGM)
phonetic information, text-independent speaker verification, adversarial
training
Embeddings extracted by deep neural networks have become the state-of-the-art
utterance representation in speaker recognition systems. It has recently been
shown that incorporating frame-level phonetic information in the embedding
extractor can improve the speaker recognition performance. On the other hand, in
the final embedding, phonetic information is just an additional source of session
variability which may be harmful to the text-independent speaker recognition
task. This suggests that at the embedding level phonetic information should be
suppressed rather than encouraged. To verify this hypothesis, we perform several
experiments that encourage or/and suppress phonetic information at various stages
in the network. Our experiments confirm that multitask learning is beneficial if
it is applied at the frame-level stage of the network, whereas adversarial
training is beneficial if it is used at the segment-level stage of the network.
Additionally, the combination of these two approaches improves the performance
further, resulting in an equal error rate of 3.17% on the VoxCeleb dataset.
@inproceedings{BUT159994,
author="WANG, S. and ROHDIN, J. and BURGET, L. and PLCHOT, O. and QIAN, Y. and YU, K. and ČERNOCKÝ, J.",
title="On the Usage of Phonetic Information for Text-independent Speaker Embedding Extraction",
booktitle="Proceedings of Interspeech",
year="2019",
journal="Proceedings of Interspeech",
volume="2019",
number="9",
pages="1148--1152",
publisher="International Speech Communication Association",
address="Graz",
doi="10.21437/Interspeech.2019-3036",
issn="1990-9772",
url="https://www.isca-speech.org/archive/Interspeech_2019/pdfs/3036.pdf"
}