Detail publikace

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

YUSUF, B. ČERNOCKÝ, J. SARAÇLAR, M.

Originální název

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

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

keyword search, spoken term detection, acoustic unit discovery

Autoři

YUSUF, B.; ČERNOCKÝ, J.; SARAÇLAR, M.

Vydáno

1. 9. 2024

Nakladatel

International Speech Communication Association

Místo

Kos

ISSN

1990-9772

Periodikum

Proceedings of Interspeech

Ročník

2024

Číslo

9

Stát

Francouzská republika

Strany od

5068

Strany do

5072

Strany počet

5

URL

https://www.isca-archive.org/interspeech_2024/yusuf24b_interspeech.pdf

BibTex

@inproceedings{BUT193671,
  author="YUSUF, B. and ČERNOCKÝ, J. and SARAÇLAR, M.",
  title="Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units",
  booktitle="Proceedings of Interspeech 2024",
  year="2024",
  journal="Proceedings of Interspeech",
  volume="2024",
  number="9",
  pages="5068--5072",
  publisher="International Speech Communication Association",
  address="Kos",
  doi="10.21437/Interspeech.2024-1713",
  issn="1990-9772",
  url="https://www.isca-archive.org/interspeech_2024/yusuf24b_interspeech.pdf"
}