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

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

Paper in proceedings (conference paper)

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.

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.

keyword search, spoken term detection, acoustic unit discovery

keyword search, spoken term detection, acoustic unit discovery

YUSUF, B.; ČERNOCKÝ, J.; SARAÇLAR, M.

2025

01.09.2024

International Speech Communication Association

Kos

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

1990-9772

Proceedings of Interspeech

2024

9

French Republic

5068

5072

5

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

yusuf24b_interspeech_2024