End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F23%3APU149429" target="_blank" >RIV/00216305:26230/23:PU149429 - isvavai.cz</a>

Result on the web

<a href="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10201906" target="_blank" >https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10201906</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TASLP.2023.3301239" target="_blank" >10.1109/TASLP.2023.3301239</a>

Result language

angličtina

Original language name

End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations

Original language description

Conventional keyword search systems operate on automatic speech recognition (ASR) outputs, which causes them to have a complex indexing and search pipeline. This has led to interest in ASR-free approaches to simplify the search procedure. We recently proposed a neural ASR-free keyword search model which achieves competitive performance while maintaining an efficient and simplified pipeline, where queries and documents are encoded with a pair of recurrent neural network encoders and the encodings are combined with a dot-product. In this article, we extend this work with multilingual pretraining and detailed analysis of the model. Our experiments show that the proposed multilingual training significantly improves the model performance and that despite not matching a strong ASR-based conventional keyword search system for short queries and queries comprising in-vocabulary words, the proposed model outperforms the ASR-based system for long queries and queries that do not appear in the training data.

Czech name

—

Czech description

—

Type

J_imp - 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)

Project

<a href="/en/project/GX19-26934X" target="_blank" >GX19-26934X: Neural Representations in Multi-modal and Multi-lingual Modeling</a><br>

Continuities

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

Publication year

2023

Confidentiality

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

Name of the periodical

IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING

ISSN

2329-9290

e-ISSN

2329-9304

Volume of the periodical

31

Issue of the periodical within the volume

08

Country of publishing house

US - UNITED STATES

Number of pages

11

Pages from-to

3070-3080

UT code for WoS article

001047323400008

EID of the result in the Scopus database

2-s2.0-85166759272