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

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F21%3APU142966" target="_blank" >RIV/00216305:26230/21:PU142966 - isvavai.cz</a>

Result on the web

<a href="https://www.isca-speech.org/archive/interspeech_2021/egorova21_interspeech.html" target="_blank" >https://www.isca-speech.org/archive/interspeech_2021/egorova21_interspeech.html</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Interspeech.2021-1756" target="_blank" >10.21437/Interspeech.2021-1756</a>

Result language

angličtina

Original language name

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

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/GX19-26934X" target="_blank" >GX19-26934X: Neural Representations in Multi-modal and Multi-lingual Modeling</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2021

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings Interspeech 2021

ISBN

—

ISSN

1990-9772

e-ISSN

—

Number of pages

5

Pages from-to

2901-2905

Publisher name

International Speech Communication Association

Place of publication

Brno

Event location

Brno

Event date

Aug 30, 2021

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000841879502201