Publication Details

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

EGOROVA Ekaterina, VYDANA Hari K., BURGET Lukáš and ČERNOCKÝ Jan. Out-of-Vocabulary Words Detection with Attention and CTC Alignments in an End-to-End ASR System. In: Proceedings Interspeech 2021. Brno: International Speech Communication Association, 2021, pp. 2901-2905. ISSN 1990-9772. Available from: https://www.isca-speech.org/archive/interspeech_2021/egorova21_interspeech.html
Czech title
Detekce slov mimo slovník pro end-to-end systém rozpoznávání řeči pomocí attention a CTC zarovnání
Type
conference paper
Language
english
Authors
URL
Keywords

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

Abstract

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.

Published
2021
Pages
2901-2905
Journal
Proceedings of Interspeech - on-line, vol. 2021, no. 8, ISSN 1990-9772
Proceedings
Proceedings Interspeech 2021
Conference
Interspeech Conference, Brno, CZ
Publisher
International Speech Communication Association
Place
Brno, CZ
DOI
UT WoS
000841879502201
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB12608,
   author = "Ekaterina Egorova and K. Hari Vydana and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}",
   title = "Out-of-Vocabulary Words Detection with Attention and CTC Alignments in an End-to-End ASR System",
   pages = "2901--2905",
   booktitle = "Proceedings Interspeech 2021",
   journal = "Proceedings of Interspeech - on-line",
   volume = 2021,
   number = 8,
   year = 2021,
   location = "Brno, CZ",
   publisher = "International Speech Communication Association",
   ISSN = "1990-9772",
   doi = "10.21437/Interspeech.2021-1756",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12608"
}
Back to top