Publication Details

i-vectors in language modeling: An efficient way of domain adaptation for feed-forward models

BENEŠ, K.; KESIRAJU, S.; BURGET, L. i-vectors in language modeling: An efficient way of domain adaptation for feed-forward models. In Proceedings of Interspeech 2018. Proceedings of Interspeech. Hyderabad: International Speech Communication Association, 2018. p. 3383-3387. ISSN: 1990-9772.
Czech title
i-vektory pro jazykové modelování: efektivní způsob doménové adaptace s dopřednými modely
Type
conference paper
Language
English
Authors
URL
Keywords

language modeling, feed-forward models, subspacemultinomial model, domain adaptation

Abstract

We show an effective way of adding context information toshallow neural language models. We propose to use SubspaceMultinomial Model (SMM) for context modeling and we addthe extracted i-vectors in a computationally efficient way. Byadding this information, we shrink the gap between shallowfeed-forward network and an LSTM from 65 to 31 points of perplexityon the Wikitext-2 corpus (in the case of neural 5-grammodel). Furthermore, we show that SMM i-vectors are suitablefor domain adaptation and a very small amount of adaptationdata (e.g. endmost 5% of a Wikipedia article) brings asubstantial improvement. Our proposed changes are compatiblewith most optimization techniques used for shallow feedforwardLMs.

Published
2018
Pages
3383–3387
Journal
Proceedings of Interspeech, vol. 2018, no. 9, ISSN 1990-9772
Proceedings
Proceedings of Interspeech 2018
Conference
Interspeech Conference, Hyderabad, India, IN
Publisher
International Speech Communication Association
Place
Hyderabad
DOI
UT WoS
000465363900706
EID Scopus
BibTeX
@inproceedings{BUT155102,
  author="Karel {Beneš} and Santosh {Kesiraju} and Lukáš {Burget}",
  title="i-vectors in language modeling: An efficient way of domain adaptation for feed-forward models",
  booktitle="Proceedings of Interspeech 2018",
  year="2018",
  journal="Proceedings of Interspeech",
  volume="2018",
  number="9",
  pages="3383--3387",
  publisher="International Speech Communication Association",
  address="Hyderabad",
  doi="10.21437/Interspeech.2018-1070",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/Interspeech_2018/abstracts/1070.html"
}
Files
Back to top