Detail publikace

Text Augmentation for Language Models in High Error Recognition Scenario

BENEŠ, K. BURGET, L.

Originální název

Text Augmentation for Language Models in High Error Recognition Scenario

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

In this paper, we explore several data augmentation strategiesfor training of language models for speech recognition. Wecompare augmentation based on global error statistics withone based on unigram statistics of ASR errors and with labelsmoothingand its sampled variant. Additionally, we investigatethe stability and the predictive power of perplexity estimatedon augmented data. Despite being trivial, augmentation drivenby global substitution, deletion and insertion rates achieves thebest rescoring results. On the other hand, even though the associatedperplexity measure is stable, it gives no better predictionof the final error rate than the vanilla one. Our best augmentationscheme increases the WER improvement from second-passrescoring from 1.1% to 1.9% absolute on the CHiMe-6 challenge.

Klíčová slova

data augmentation, error simulation, languagemodeling, automatic speech recognition

Autoři

BENEŠ, K.; BURGET, L.

Vydáno

30. 8. 2021

Nakladatel

International Speech Communication Association

Místo

Brno

ISSN

1990-9772

Periodikum

Proceedings of Interspeech

Ročník

2021

Číslo

8

Stát

Francouzská republika

Strany od

1872

Strany do

1876

Strany počet

5

URL

https://www.isca-speech.org/archive/interspeech_2021/benes21_interspeech.html

BibTex

@inproceedings{BUT175841,
  author="Karel {Beneš} and Lukáš {Burget}",
  title="Text Augmentation for Language Models in High Error Recognition Scenario",
  booktitle="Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
  year="2021",
  journal="Proceedings of Interspeech",
  volume="2021",
  number="8",
  pages="1872--1876",
  publisher="International Speech Communication Association",
  address="Brno",
  doi="10.21437/Interspeech.2021-627",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/interspeech_2021/benes21_interspeech.html"
}

Dokumenty

benes21_interspeech.pdf