Detail publikace

Training Data Augmentation and Data Selection

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

Originální název

Training Data Augmentation and Data Selection

Typ

kapitola v knize

Jazyk

angličtina

Originální abstrakt

Data augmentation is a simple and efficient technique to improve the robustness of a speech recognizer when deployed in mismatched training-test conditions. Our work, conducted during the JSALT 2015 workshop, aimed at the development of: (1) Data augmentation strategies including noising and reverberation. They were tested in combination with two approaches to signal enhancement: a carefully engineered WPE dereverberation and a learned DNN-based denoising autoencoder. (2) Proposing a novel technique for extracting an informative vector from 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 can be used directly for adaptation, but the main usage matching the aim of this chapter is for selection of augmented training data. All techniques were tested on the AMI training set and CHiME3 test set.

Klíčová slova

training data, augmentation, data selection

Autoři

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

Vydáno

8. 12. 2017

Nakladatel

Springer International Publishing

Místo

Heidelberg

ISBN

978-3-319-64679-4

Kniha

New Era for Robust Speech Recognition: Exploiting Deep Learning

Edice

Computer Science, Artificial Intelligence

Strany od

245

Strany do

260

Strany počet

16

URL

http://www.springer.com/gp/book/9783319646794#aboutBook

BibTex

@inbook{BUT144497,
  author="Martin {Karafiát} and Karel {Veselý} and Kateřina {Žmolíková} and Marc {Delcroix} and Shinji {Watanabe} and Lukáš {Burget} and Jan {Černocký} and Igor {Szőke}",
  title="Training Data Augmentation and Data Selection",
  booktitle="New Era for Robust Speech Recognition: Exploiting Deep Learning",
  year="2017",
  publisher="Springer International Publishing",
  address="Heidelberg",
  series="Computer Science, Artificial Intelligence",
  pages="245--260",
  doi="10.1007/978-3-319-64680-0\{_}10",
  isbn="978-3-319-64679-4",
  url="http://www.springer.com/gp/book/9783319646794#aboutBook"
}