Detail publikace

Semi-Supervised Bootstrapping Approach For Neural Network Feature Extractor Training

GRÉZL, F. KARAFIÁT, M.

Originální název

Semi-Supervised Bootstrapping Approach For Neural Network Feature Extractor Training

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

This paper presents bootstrapping approach for training the Bottle-Neck neural network feature extractor which provides features  for subsequent GMM-HMM recognizer. One can use this recognizer to automatically transcribe the unsupervised data and assign the confidence of the transcription. Based on the confidence, segments are selected and mixed with supervised data and new NNs are trained. The automatic transcription can recover 40-55% in comparison to manually transcribed data. This is 3 to 5% absolute improvement over NN trained on supervised data only. Using 70-85% of automatically transcribed segments with the highest confidence was found optimal to achieve this result. Dropping the rest of the data prevents training on low quality transcripts.

Klíčová slova

Semi-supervised training, bootstrapping, bottle-neck features

Autoři

GRÉZL, F.; KARAFIÁT, M.

Rok RIV

2013

Vydáno

8. 12. 2013

Nakladatel

IEEE Signal Processing Society

Místo

Olomouc

ISBN

978-1-4799-2755-5

Kniha

Proceedings of ASRU 2013

Strany od

470

Strany do

475

Strany počet

6

URL

http://www.fit.vutbr.cz/research/groups/speech/publi/2013/grezl_asru2013_0000470.pdf

BibTex

@inproceedings{BUT105972,
  author="František {Grézl} and Martin {Karafiát}",
  title="Semi-Supervised Bootstrapping Approach For Neural Network Feature Extractor Training",
  booktitle="Proceedings of ASRU 2013",
  year="2013",
  pages="470--475",
  publisher="IEEE Signal Processing Society",
  address="Olomouc",
  isbn="978-1-4799-2755-5",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2013/grezl_asru2013_0000470.pdf"
}