Detail publikace

Sequence Summarizing Neural Network for Speaker Adaptation

VESELÝ, K. WATANABE, S. ŽMOLÍKOVÁ, K. KARAFIÁT, M. BURGET, L. ČERNOCKÝ, J.

Originální název

Sequence Summarizing Neural Network for Speaker Adaptation

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

In this paper, we propose a DNN adaptation technique, where the i-vector extractor is replaced by a Sequence Summarizing Neural Network (SSNN). Similarly to i-vector extractor, the SSNN produces a "summary vector", representing an acoustic summary of an utterance. Such vector is then appended to the input of main network, while both networks are trained together optimizing single loss function. Both the i-vector and SSNN speaker adaptation methods are compared on AMI meeting data. The results show comparable performance of both techniques on FBANK system with frameclassification training. Moreover, appending both the i-vector and "summary vector" to the FBANK features leads to additional improvement comparable to the performance of FMLLR adapted DNN system.

Klíčová slova

DNN, adaptation, i-vector, sequence summary, SSNN

Autoři

VESELÝ, K.; WATANABE, S.; ŽMOLÍKOVÁ, K.; KARAFIÁT, M.; BURGET, L.; ČERNOCKÝ, J.

Vydáno

20. 3. 2016

Nakladatel

IEEE Signal Processing Society

Místo

Shanghai

ISBN

978-1-4799-9988-0

Kniha

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

Strany od

5315

Strany do

5319

Strany počet

5

URL

https://www.fit.vut.cz/research/publication/11145/

BibTex

@inproceedings{BUT130964,
  author="Karel {Veselý} and Shinji {Watanabe} and Kateřina {Žmolíková} and Martin {Karafiát} and Lukáš {Burget} and Jan {Černocký}",
  title="Sequence Summarizing Neural Network for Speaker Adaptation",
  booktitle="Proceedings of the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016",
  year="2016",
  pages="5315--5319",
  publisher="IEEE Signal Processing Society",
  address="Shanghai",
  doi="10.1109/ICASSP.2016.7472692",
  isbn="978-1-4799-9988-0",
  url="https://www.fit.vut.cz/research/publication/11145/"
}