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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Papi, Sara, Polak, Peter, Bojar, Ondřej, Macháček, Dominik
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910762058907648
author Papi, Sara
Polak, Peter
Bojar, Ondřej
Macháček, Dominik
author_facet Papi, Sara
Polak, Peter
Bojar, Ondřej
Macháček, Dominik
contents Simultaneous speech-to-text translation (SimulST) translates source-language speech into target-language text concurrently with the speaker'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, 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 literature, from evaluation frameworks to system architectures, for advancing the field towards more realistic and effective SimulST solutions.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18495
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?
Papi, Sara
Polak, Peter
Bojar, Ondřej
Macháček, Dominik
Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
Simultaneous speech-to-text translation (SimulST) translates source-language speech into target-language text concurrently with the speaker'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, 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 literature, from evaluation frameworks to system architectures, for advancing the field towards more realistic and effective SimulST solutions.
title How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?
topic Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2412.18495