@inproceedings{sethiya-etal-2024-indic-tedst,
title = "{I}ndic-{TEDST}: Datasets and Baselines for Low-Resource Speech to Text Translation",
author = "Sethiya, Nivedita and
Nair, Saanvi and
Maurya, Chandresh",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.790",
pages = "9019--9024",
abstract = "Speech-to-text (ST) task is the translation of speech in a language to text in a different language. It has use cases in subtitling, dubbing, etc. Traditionally, ST task has been solved by cascading automatic speech recognition (ASR) and machine translation (MT) models which leads to error propagation, high latency, and training time. To minimize such issues, end-to-end models have been proposed recently. However, we find that only a few works have reported results of ST models on a limited number of low-resource languages. To take a step further in this direction, we release datasets and baselines for low-resource ST tasks. Concretely, our dataset has 9 language pairs and benchmarking has been done against SOTA ST models. The low performance of SOTA ST models on Indic-TEDST data indicates the necessity of the development of ST models specifically designed for low-resource languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sethiya-etal-2024-indic-tedst">
<titleInfo>
<title>Indic-TEDST: Datasets and Baselines for Low-Resource Speech to Text Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nivedita</namePart>
<namePart type="family">Sethiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saanvi</namePart>
<namePart type="family">Nair</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chandresh</namePart>
<namePart type="family">Maurya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Speech-to-text (ST) task is the translation of speech in a language to text in a different language. It has use cases in subtitling, dubbing, etc. Traditionally, ST task has been solved by cascading automatic speech recognition (ASR) and machine translation (MT) models which leads to error propagation, high latency, and training time. To minimize such issues, end-to-end models have been proposed recently. However, we find that only a few works have reported results of ST models on a limited number of low-resource languages. To take a step further in this direction, we release datasets and baselines for low-resource ST tasks. Concretely, our dataset has 9 language pairs and benchmarking has been done against SOTA ST models. The low performance of SOTA ST models on Indic-TEDST data indicates the necessity of the development of ST models specifically designed for low-resource languages.</abstract>
<identifier type="citekey">sethiya-etal-2024-indic-tedst</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.790</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9019</start>
<end>9024</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Indic-TEDST: Datasets and Baselines for Low-Resource Speech to Text Translation
%A Sethiya, Nivedita
%A Nair, Saanvi
%A Maurya, Chandresh
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F sethiya-etal-2024-indic-tedst
%X Speech-to-text (ST) task is the translation of speech in a language to text in a different language. It has use cases in subtitling, dubbing, etc. Traditionally, ST task has been solved by cascading automatic speech recognition (ASR) and machine translation (MT) models which leads to error propagation, high latency, and training time. To minimize such issues, end-to-end models have been proposed recently. However, we find that only a few works have reported results of ST models on a limited number of low-resource languages. To take a step further in this direction, we release datasets and baselines for low-resource ST tasks. Concretely, our dataset has 9 language pairs and benchmarking has been done against SOTA ST models. The low performance of SOTA ST models on Indic-TEDST data indicates the necessity of the development of ST models specifically designed for low-resource languages.
%U https://aclanthology.org/2024.lrec-main.790
%P 9019-9024
Markdown (Informal)
[Indic-TEDST: Datasets and Baselines for Low-Resource Speech to Text Translation](https://aclanthology.org/2024.lrec-main.790) (Sethiya et al., LREC-COLING 2024)
ACL