How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511524" target="_blank" >RIV/00216208:11320/25:10511524 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=Tr5Ykr6_ID" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=Tr5Ykr6_ID</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1162/tacl_a_00740" target="_blank" >10.1162/tacl_a_00740</a>

Jazyk výsledku

angličtina

Název v původním jazyce

How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?

Popis výsledku v původním jazyce

Simultaneous speech-to-text translation (SimulST) translates source-language speech into target-language text concurrently with the speaker&apos;s speech, ensuring low latency for better user comprehension. Despite its intended application to unbounded speech, most research has focused on human pre-segmented speech, simplifying the task and overlooking significant challenges. This narrow focus, coupled with widespread terminological inconsistencies affecting the task, is limiting the applicability of research outcomes to real-world applications, ultimately hindering progress in the field. Our extensive literature review of 110 papers not only reveals these critical issues in current research but also serves as the foundation for our key contributions, we: 1) define the steps and core components of a SimulST system, proposing a standardized terminology and taxonomy, 2) conduct a thorough analysis of community trends, and 3) offer concrete recommendations and future directions to bridge the gaps in existing

Název v anglickém jazyce

How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?

Popis výsledku anglicky

Simultaneous speech-to-text translation (SimulST) translates source-language speech into target-language text concurrently with the speaker&apos;s speech, ensuring low latency for better user comprehension. Despite its intended application to unbounded speech, most research has focused on human pre-segmented speech, simplifying the task and overlooking significant challenges. This narrow focus, coupled with widespread terminological inconsistencies affecting the task, is limiting the applicability of research outcomes to real-world applications, ultimately hindering progress in the field. Our extensive literature review of 110 papers not only reveals these critical issues in current research but also serves as the foundation for our key contributions, we: 1) define the steps and core components of a SimulST system, proposing a standardized terminology and taxonomy, 2) conduct a thorough analysis of community trends, and 3) offer concrete recommendations and future directions to bridge the gaps in existing

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

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název periodika

Transactions of the Association for Computational Linguistics

ISSN

2307-387X

e-ISSN

—

Svazek periodika

13

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

33

Strana od-do

281-313

Kód UT WoS článku

001468634000001

EID výsledku v databázi Scopus

2-s2.0-105010240370