Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F24%3APU154929" target="_blank" >RIV/00216305:26230/24:PU154929 - isvavai.cz</a>

Result on the web

<a href="https://www.isca-archive.org/interspeech_2024/yusuf24b_interspeech.pdf" target="_blank" >https://www.isca-archive.org/interspeech_2024/yusuf24b_interspeech.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Interspeech.2024-1713" target="_blank" >10.21437/Interspeech.2024-1713</a>

Result language

angličtina

Original language name

Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units

Original language description

End-to-end (E2E) keyword search (KWS) has emerged as an alternative and complimentary approach to conventional key- word search which depends on the output of automatic speech recognition (ASR) systems. While E2E methods greatly sim- plify the KWS pipeline, they generally have worse performance than their ASR-based counterparts, which can benefit from pretraining with untranscribed data. In this work, we propose a method for pretraining E2E KWS systems with untranscribed data, which involves using acoustic unit discovery (AUD) to obtain discrete units for untranscribed data and then learning to locate sequences of such units in the speech. We conduct exper- iments across languages and AUD systems: we show that finetuning such a model significantly outperforms a model trained from scratch, and the performance improvements are generally correlated with the quality of the AUD system used for pretraining.

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/VJ01010108" target="_blank" >VJ01010108: Robust processing of recordings for operations and security</a><br>

Continuities

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

Publication year

2024

Confidentiality

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

Article name in the collection

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

ISBN

—

ISSN

1990-9772

e-ISSN

—

Number of pages

5

Pages from-to

5068-5072

Publisher name

International Speech Communication Association

Place of publication

Kos

Event location

Kos

Event date

Sep 1, 2024

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—