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

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

<a href="/cs/project/VJ01010108" target="_blank" >VJ01010108: Robustní zpracování nahrávek pro operativu a bezpečnost</a><br>

Návaznosti

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

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

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

ISBN

—

ISSN

1990-9772

e-ISSN

—

Počet stran výsledku

5

Strana od-do

5068-5072

Název nakladatele

International Speech Communication Association

Místo vydání

Kos

Místo konání akce

Kos

Datum konání akce

1. 9. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—