Written Term Detection Improves Spoken Term Detection
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F24%3APU154756" target="_blank" >RIV/00216305:26230/24:PU154756 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/document/10571348" target="_blank" >https://ieeexplore.ieee.org/document/10571348</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/TASLP.2024.3407476" target="_blank" >10.1109/TASLP.2024.3407476</a>
Alternative languages
Result language
angličtina
Original language name
Written Term Detection Improves Spoken Term Detection
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
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)
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING
ISSN
2329-9290
e-ISSN
2329-9304
Volume of the periodical
32
Issue of the periodical within the volume
06
Country of publishing house
US - UNITED STATES
Number of pages
11
Pages from-to
3213-3223
UT code for WoS article
001256333200007
EID of the result in the Scopus database
2-s2.0-85198013158