Resources and Benchmarks for Keyword Search in Spoken Audio From Low-Resource Indian Languages

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F22%3APU147441" target="_blank" >RIV/00216305:26230/22:PU147441 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9743904" target="_blank" >https://ieeexplore.ieee.org/document/9743904</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ACCESS.2022.3162854" target="_blank" >10.1109/ACCESS.2022.3162854</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Resources and Benchmarks for Keyword Search in Spoken Audio From Low-Resource Indian Languages

Popis výsledku v původním jazyce

This paper presents the resources and benchmarks developed for keyword search (KWS) in spoken audio from six low-resource Indian languages (from two families), namely Gujarati, Hindi, Marathi, Odia, Tamil, and Telugu. The current work on constructing keywords and building benchmark KWS systems is inspired by the popular IARPA Babel program and the subsequent works on low-resource KWS. The keywords are constructed by taking into account their properties i.e., occurrence, length, and average confusability; and their effects on the evaluation metric - the term-weighted value (TWV).We make use of freely available speech datasets, and reprocess them to create resources for KWS, thereby adding value to the existing speech resources. Four ASR-based KWS systems are built, and their performance is analyzed across the three keyword properties on all the six languages. The prepared keywords and other related resources to replicate our experiments are made available for the public.We believe that the analysis and guidelines provided in this paper will not only help the research community, but also practitioners and engineers to easily create KWS resources for newer languages, datasets, and scenarios.

Název v anglickém jazyce

Resources and Benchmarks for Keyword Search in Spoken Audio From Low-Resource Indian Languages

Popis výsledku anglicky

This paper presents the resources and benchmarks developed for keyword search (KWS) in spoken audio from six low-resource Indian languages (from two families), namely Gujarati, Hindi, Marathi, Odia, Tamil, and Telugu. The current work on constructing keywords and building benchmark KWS systems is inspired by the popular IARPA Babel program and the subsequent works on low-resource KWS. The keywords are constructed by taking into account their properties i.e., occurrence, length, and average confusability; and their effects on the evaluation metric - the term-weighted value (TWV).We make use of freely available speech datasets, and reprocess them to create resources for KWS, thereby adding value to the existing speech resources. Four ASR-based KWS systems are built, and their performance is analyzed across the three keyword properties on all the six languages. The prepared keywords and other related resources to replicate our experiments are made available for the public.We believe that the analysis and guidelines provided in this paper will not only help the research community, but also practitioners and engineers to easily create KWS resources for newer languages, datasets, and scenarios.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GX19-26934X" target="_blank" >GX19-26934X: Neuronové reprezentace v multimodálním a mnohojazyčném modelování</a><br>

Návaznosti

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

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název periodika

IEEE Access

ISSN

2169-3536

e-ISSN

—

Svazek periodika

10

Číslo periodika v rámci svazku

2022

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

11

Strana od-do

34789-34799

Kód UT WoS článku

000778878900001

EID výsledku v databázi Scopus

2-s2.0-85127473918