@inproceedings{denisov-vu-2024-teaching,
title = "Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training",
author = "Denisov, Pavel and
Vu, Thang",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.52",
doi = "10.18653/v1/2024.findings-naacl.52",
pages = "814--834",
abstract = "Recent advancements in language modeling have led to the emergenceof Large Language Models (LLMs) capable ofvarious natural language processing tasks.Despite their success in text-based tasks, applying LLMs to the speech domainremains limited and challenging. This paper presents BLOOMZMMS, a novel modelthat integrates a multilingual LLM with a multilingual speech encoder,aiming to harness the capabilities of LLMs for speech recognition and beyond.Utilizing a multi-instructional training approach, we demonstrate the transferabilityof linguistic knowledge from the text to the speech modality.Our experiments, conducted on 1900 hours of transcribed data from 139 languages,establish that a multilingual speech representation can be effectivelylearned and aligned with a multilingual LLM. While this learned representationinitially shows limitations in task generalization, we address this issue bygenerating synthetic targets in a multi-instructional style.Our zero-shot evaluation results confirm the robustness of our approach acrossmultiple tasks, including speech translation and multilingual spoken languageunderstanding, thereby opening new avenues for applying LLMs in the speech domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="denisov-vu-2024-teaching">
<titleInfo>
<title>Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Denisov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thang</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advancements in language modeling have led to the emergenceof Large Language Models (LLMs) capable ofvarious natural language processing tasks.Despite their success in text-based tasks, applying LLMs to the speech domainremains limited and challenging. This paper presents BLOOMZMMS, a novel modelthat integrates a multilingual LLM with a multilingual speech encoder,aiming to harness the capabilities of LLMs for speech recognition and beyond.Utilizing a multi-instructional training approach, we demonstrate the transferabilityof linguistic knowledge from the text to the speech modality.Our experiments, conducted on 1900 hours of transcribed data from 139 languages,establish that a multilingual speech representation can be effectivelylearned and aligned with a multilingual LLM. While this learned representationinitially shows limitations in task generalization, we address this issue bygenerating synthetic targets in a multi-instructional style.Our zero-shot evaluation results confirm the robustness of our approach acrossmultiple tasks, including speech translation and multilingual spoken languageunderstanding, thereby opening new avenues for applying LLMs in the speech domain.</abstract>
<identifier type="citekey">denisov-vu-2024-teaching</identifier>
<identifier type="doi">10.18653/v1/2024.findings-naacl.52</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.52</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>814</start>
<end>834</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training
%A Denisov, Pavel
%A Vu, Thang
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F denisov-vu-2024-teaching
%X Recent advancements in language modeling have led to the emergenceof Large Language Models (LLMs) capable ofvarious natural language processing tasks.Despite their success in text-based tasks, applying LLMs to the speech domainremains limited and challenging. This paper presents BLOOMZMMS, a novel modelthat integrates a multilingual LLM with a multilingual speech encoder,aiming to harness the capabilities of LLMs for speech recognition and beyond.Utilizing a multi-instructional training approach, we demonstrate the transferabilityof linguistic knowledge from the text to the speech modality.Our experiments, conducted on 1900 hours of transcribed data from 139 languages,establish that a multilingual speech representation can be effectivelylearned and aligned with a multilingual LLM. While this learned representationinitially shows limitations in task generalization, we address this issue bygenerating synthetic targets in a multi-instructional style.Our zero-shot evaluation results confirm the robustness of our approach acrossmultiple tasks, including speech translation and multilingual spoken languageunderstanding, thereby opening new avenues for applying LLMs in the speech domain.
%R 10.18653/v1/2024.findings-naacl.52
%U https://aclanthology.org/2024.findings-naacl.52
%U https://doi.org/10.18653/v1/2024.findings-naacl.52
%P 814-834
Markdown (Informal)
[Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training](https://aclanthology.org/2024.findings-naacl.52) (Denisov & Vu, Findings 2024)
ACL