Publication detail

Written Term Detection Improves Spoken Term Detection

YUSUF, B. SARAÇLAR, M.

Original Title

Written Term Detection Improves Spoken Term Detection

Type

journal article in Web of Science

Language

English

Original Abstract

End-to-end (E2E) approaches to keyword search (KWS) are considerably simpler in terms of training and indexing complexity when compared to approaches which use the output of automatic speech recognition (ASR) systems. This simplification however has drawbacks due to the loss of modularity. In partic- ular, where ASR-based KWS systems can benefit from external unpaired text via a language model, current formulations of E2E KWS systems have no such mechanism. Therefore, in this paper, we propose a multitask training objective which allows unpaired text to be integrated into E2E KWS without complicating indexing and search. In addition to training an E2E KWS model to retrieve text queries from spoken documents, we jointly train it to retrieve text queries from masked written documents. We show empirically that this approach can effectively leverage unpaired text for KWS, with significant improvements in search performance across a wide variety of languages. We conduct analysis which indicates that these improvements are achieved because the proposed method improves document representations for words in the unpaired text. Finally, we show that the proposed method can be used for domain adaptation in settings where in-domain paired data is scarce or nonexistent.

Keywords

Keyword search, spoken term detection, keyword spotting, end-to-end keyword search, multitask learning, domain adaptation, masked language modeling.

Authors

YUSUF, B.; SARAÇLAR, M.

Released

25. 6. 2024

ISBN

2329-9290

Periodical

IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING

Year of study

32

Number

06

State

United States of America

Pages from

3213

Pages to

3223

Pages count

11

URL

https://ieeexplore.ieee.org/document/10571348

BibTex

@article{BUT193391,
  author="YUSUF, B. and SARAÇLAR, M.",
  title="Written Term Detection Improves Spoken Term Detection",
  journal="IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING",
  year="2024",
  volume="32",
  number="06",
  pages="3213--3223",
  doi="10.1109/TASLP.2024.3407476",
  issn="2329-9290",
  url="https://ieeexplore.ieee.org/document/10571348"
}

Documents

yusuf_2024_Written_Term_Detection_Improves_Spoken_Term_Detection.pdf