@inproceedings{e-ortega-etal-2024-quespa,
title = "{QUESPA} Submission for the {IWSLT} 2024 Dialectal and Low-resource Speech Translation Task",
author = "E. Ortega, John and
Joel Zevallos, Rodolfo and
Said Ahmad, Ibrahim and
Chen, William",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Carpuat, Marine",
booktitle = "Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.iwslt-1.17/",
doi = "10.18653/v1/2024.iwslt-1.17",
pages = "125--133",
abstract = "This article describes the QUESPA team speech translation (ST) submissions for the Quechua to Spanish (QUE{--}SPA) track featured in the Evaluation Campaign of IWSLT 2024: dialectal and low-resource speech translation. Two main submission types were supported in the campaign: constrained and unconstrained. This is our second year submitting our ST systems to the IWSLT shared task and we feel that we have achieved novel performance, surpassing last year`s submissions. Again, we were able to submit six total systems of which our best (primary) constrained system consisted of an ST model based on the Fairseq S2T framework where the audio representations were created using log mel-scale filter banks as features and the translations were performed using a transformer. The system was similar to last year`s submission with slight configuration changes, allowing us to achieve slightly higher performance (2 BLEU). Contrastingly, we were able to achieve much better performance than last year on the unconstrained task using a larger pre-trained language (PLM) model for ST (without cascading) and the inclusion of parallel QUE{--}SPA data found on the internet. The fine-tuning of Microsoft`s SpeechT5 model in a ST setting along with the addition of new data and a data augmentation technique allowed us to achieve 19.7 BLEU. Additionally, we present the other four submissions (2 constrained and 2 unconstrained) which are part of additional efforts of hyper-parameter and configuration tuning on existent models and the inclusion of Whisper for speech recognition"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="e-ortega-etal-2024-quespa">
<titleInfo>
<title>QUESPA Submission for the IWSLT 2024 Dialectal and Low-resource Speech Translation Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">E. Ortega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodolfo</namePart>
<namePart type="family">Joel Zevallos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Said Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article describes the QUESPA team speech translation (ST) submissions for the Quechua to Spanish (QUE–SPA) track featured in the Evaluation Campaign of IWSLT 2024: dialectal and low-resource speech translation. Two main submission types were supported in the campaign: constrained and unconstrained. This is our second year submitting our ST systems to the IWSLT shared task and we feel that we have achieved novel performance, surpassing last year‘s submissions. Again, we were able to submit six total systems of which our best (primary) constrained system consisted of an ST model based on the Fairseq S2T framework where the audio representations were created using log mel-scale filter banks as features and the translations were performed using a transformer. The system was similar to last year‘s submission with slight configuration changes, allowing us to achieve slightly higher performance (2 BLEU). Contrastingly, we were able to achieve much better performance than last year on the unconstrained task using a larger pre-trained language (PLM) model for ST (without cascading) and the inclusion of parallel QUE–SPA data found on the internet. The fine-tuning of Microsoft‘s SpeechT5 model in a ST setting along with the addition of new data and a data augmentation technique allowed us to achieve 19.7 BLEU. Additionally, we present the other four submissions (2 constrained and 2 unconstrained) which are part of additional efforts of hyper-parameter and configuration tuning on existent models and the inclusion of Whisper for speech recognition</abstract>
<identifier type="citekey">e-ortega-etal-2024-quespa</identifier>
<identifier type="doi">10.18653/v1/2024.iwslt-1.17</identifier>
<location>
<url>https://aclanthology.org/2024.iwslt-1.17/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>125</start>
<end>133</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QUESPA Submission for the IWSLT 2024 Dialectal and Low-resource Speech Translation Task
%A E. Ortega, John
%A Joel Zevallos, Rodolfo
%A Said Ahmad, Ibrahim
%A Chen, William
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand (in-person and online)
%F e-ortega-etal-2024-quespa
%X This article describes the QUESPA team speech translation (ST) submissions for the Quechua to Spanish (QUE–SPA) track featured in the Evaluation Campaign of IWSLT 2024: dialectal and low-resource speech translation. Two main submission types were supported in the campaign: constrained and unconstrained. This is our second year submitting our ST systems to the IWSLT shared task and we feel that we have achieved novel performance, surpassing last year‘s submissions. Again, we were able to submit six total systems of which our best (primary) constrained system consisted of an ST model based on the Fairseq S2T framework where the audio representations were created using log mel-scale filter banks as features and the translations were performed using a transformer. The system was similar to last year‘s submission with slight configuration changes, allowing us to achieve slightly higher performance (2 BLEU). Contrastingly, we were able to achieve much better performance than last year on the unconstrained task using a larger pre-trained language (PLM) model for ST (without cascading) and the inclusion of parallel QUE–SPA data found on the internet. The fine-tuning of Microsoft‘s SpeechT5 model in a ST setting along with the addition of new data and a data augmentation technique allowed us to achieve 19.7 BLEU. Additionally, we present the other four submissions (2 constrained and 2 unconstrained) which are part of additional efforts of hyper-parameter and configuration tuning on existent models and the inclusion of Whisper for speech recognition
%R 10.18653/v1/2024.iwslt-1.17
%U https://aclanthology.org/2024.iwslt-1.17/
%U https://doi.org/10.18653/v1/2024.iwslt-1.17
%P 125-133
Markdown (Informal)
[QUESPA Submission for the IWSLT 2024 Dialectal and Low-resource Speech Translation Task](https://aclanthology.org/2024.iwslt-1.17/) (E. Ortega et al., IWSLT 2024)
ACL