Detail publikace

Out-of-Vocabulary Words Detection with Attention and CTC Alignments in an End-to-End ASR System

EGOROVA, E. VYDANA, H. BURGET, L. ČERNOCKÝ, J.

Originální název

Out-of-Vocabulary Words Detection with Attention and CTC Alignments in an End-to-End ASR System

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

This work explores the effectiveness of detecting positions of out-of-vocabulary words (OOVs) in a decoded utterance using attention weights and CTC per-frame outputs of an end-to-end system predicting word sequences. We show that the end-to-end approach can be effective for the task of OOV detection. CTC alignments are shown to provide better temporal information about the positions of OOV words than attention, and therefore are more suitable for the task. The detected positions of OOV occurrences are utilized for the recurrent OOV recovery task in which probabilistic representations of the pronunciations of the detected OOVs are clustered in order to find repeating words. Improved detection results are shown to correlate with better performance of the recovery of recurrent OOVs.

Klíčová slova

Speech recognition, Out-of-vocabulary, OOV, Attention, CTC, End-to-end

Autoři

EGOROVA, E.; VYDANA, H.; BURGET, L.; ČERNOCKÝ, J.

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

2901

Strany do

2905

Strany počet

5

URL

https://www.isca-speech.org/archive/interspeech_2021/egorova21_interspeech.html

BibTex

@inproceedings{BUT175843,
  author="Ekaterina {Egorova} and Hari Krishna {Vydana} and Lukáš {Burget} and Jan {Černocký}",
  title="Out-of-Vocabulary Words Detection with Attention and CTC Alignments in an End-to-End ASR System",
  booktitle="Proceedings Interspeech 2021",
  year="2021",
  journal="Proceedings of Interspeech",
  volume="2021",
  number="8",
  pages="2901--2905",
  publisher="International Speech Communication Association",
  address="Brno",
  doi="10.21437/Interspeech.2021-1756",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/interspeech_2021/egorova21_interspeech.html"
}