Publication result detail

Semi-Supervised Bootstrapping Approach For Neural Network Feature Extractor Training

GRÉZL, F.; KARAFIÁT, M.

Original Title

Semi-Supervised Bootstrapping Approach For Neural Network Feature Extractor Training

English Title

Semi-Supervised Bootstrapping Approach For Neural Network Feature Extractor Training

Type

Paper in proceedings outside WoS and Scopus

Original Abstract

This paper presents bootstrapping approach for training the Bottle-Neck neural networkfeature 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, segmentsare selected and mixed with supervised data and newNNs are trained. The automatic transcription can recover 40-55% in comparison to manually transcribed data. This is 3 to 5% absolute improvement over NN trainedon supervised data only. Using 70-85% of automaticallytranscribed segments with the highest confidence was foundoptimal to achieve this result. Dropping the rest of the data prevents training on low quality transcripts.

English abstract

This paper presents bootstrapping approach for training the Bottle-Neck neural networkfeature 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, segmentsare selected and mixed with supervised data and newNNs are trained. The automatic transcription can recover 40-55% in comparison to manually transcribed data. This is 3 to 5% absolute improvement over NN trainedon supervised data only. Using 70-85% of automaticallytranscribed segments with the highest confidence was foundoptimal to achieve this result. Dropping the rest of the data prevents training on low quality transcripts.

Keywords

Semi-supervised training, bootstrapping,bottle-neck features

Key words in English

Semi-supervised training, bootstrapping,bottle-neck features

Authors

GRÉZL, F.; KARAFIÁT, M.

RIV year

2014

Released

08.12.2013

Publisher

IEEE Signal Processing Society

Location

Olomouc

ISBN

978-1-4799-2755-5

Book

Proceedings of ASRU 2013

Pages from

470

Pages to

475

Pages count

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"
}