@inproceedings{riyadh-etal-2026-speechlm,
title = "{S}peech{LM} for Automatic Speech Recognition in Low-resource Languages",
author = "Riyadh, Md Abdur Razzaq and
Agirre, Eneko and
Navas, Eva and
Borg, Claudia",
editor = "Hosseini-Kivanani, Nina and
Brutti, Alessio and
Matassoni, Marco and
Dowerah, Sandipana and
Liga, Davide and
Schommer, Christoph",
booktitle = "Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis ({SPEAKABLE}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.speakable-1.14/",
doi = "10.63317/2634e2pv97js",
pages = "125--131",
abstract = "Multi-modal Speech Language Models (SpeechLMs) are a recent advancement in natural language processing. These SpeechLMs are instruction-tuned and optimized for general tasks. Their usefulness for Automatic Speech Recognition (ASR), particularly in relatively low-resource scenarios, remains largely understudied. This work developed SpeechLM for ASR in Basque and Maltese and studied the impact of language-adapted Large Language Model (LLM) and speech encoder within the SpeechLM for ASR. Using supervised learning, we fine-tuned LLaMA-Omni, a SpeechLM, for ASR. We have conducted comprehensive hyperparameter tuning and experimented with language-adapted SpeechLM components to improve performance and evaluated our best models on in-distribution datasets for both languages and an out-of-distribution dataset for Basque. LLaMA-Omni achieved 8.09{\%} WER in Basque and 25.65{\%} WER for Maltese on average across multiple test splits. The in-distribution results show that SpeechLM outperforms a fine-tuned ASR system under specific constraints, whereas it underperforms the baseline model on out-of-distribution Basque, indicating weaker overall robustness. We also find that a language-adapted LLM within SpeechLM improves in out-of-distribution settings when compared to the off-the-shelf LLM within SpeechLM."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="riyadh-etal-2026-speechlm">
<titleInfo>
<title>SpeechLM for Automatic Speech Recognition in Low-resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Abdur</namePart>
<namePart type="given">Razzaq</namePart>
<namePart type="family">Riyadh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eneko</namePart>
<namePart type="family">Agirre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Navas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Borg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Hosseini-Kivanani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessio</namePart>
<namePart type="family">Brutti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Matassoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandipana</namePart>
<namePart type="family">Dowerah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davide</namePart>
<namePart type="family">Liga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="family">Schommer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-modal Speech Language Models (SpeechLMs) are a recent advancement in natural language processing. These SpeechLMs are instruction-tuned and optimized for general tasks. Their usefulness for Automatic Speech Recognition (ASR), particularly in relatively low-resource scenarios, remains largely understudied. This work developed SpeechLM for ASR in Basque and Maltese and studied the impact of language-adapted Large Language Model (LLM) and speech encoder within the SpeechLM for ASR. Using supervised learning, we fine-tuned LLaMA-Omni, a SpeechLM, for ASR. We have conducted comprehensive hyperparameter tuning and experimented with language-adapted SpeechLM components to improve performance and evaluated our best models on in-distribution datasets for both languages and an out-of-distribution dataset for Basque. LLaMA-Omni achieved 8.09% WER in Basque and 25.65% WER for Maltese on average across multiple test splits. The in-distribution results show that SpeechLM outperforms a fine-tuned ASR system under specific constraints, whereas it underperforms the baseline model on out-of-distribution Basque, indicating weaker overall robustness. We also find that a language-adapted LLM within SpeechLM improves in out-of-distribution settings when compared to the off-the-shelf LLM within SpeechLM.</abstract>
<identifier type="citekey">riyadh-etal-2026-speechlm</identifier>
<identifier type="doi">10.63317/2634e2pv97js</identifier>
<location>
<url>https://aclanthology.org/2026.speakable-1.14/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>125</start>
<end>131</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SpeechLM for Automatic Speech Recognition in Low-resource Languages
%A Riyadh, Md Abdur Razzaq
%A Agirre, Eneko
%A Navas, Eva
%A Borg, Claudia
%Y Hosseini-Kivanani, Nina
%Y Brutti, Alessio
%Y Matassoni, Marco
%Y Dowerah, Sandipana
%Y Liga, Davide
%Y Schommer, Christoph
%S Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F riyadh-etal-2026-speechlm
%X Multi-modal Speech Language Models (SpeechLMs) are a recent advancement in natural language processing. These SpeechLMs are instruction-tuned and optimized for general tasks. Their usefulness for Automatic Speech Recognition (ASR), particularly in relatively low-resource scenarios, remains largely understudied. This work developed SpeechLM for ASR in Basque and Maltese and studied the impact of language-adapted Large Language Model (LLM) and speech encoder within the SpeechLM for ASR. Using supervised learning, we fine-tuned LLaMA-Omni, a SpeechLM, for ASR. We have conducted comprehensive hyperparameter tuning and experimented with language-adapted SpeechLM components to improve performance and evaluated our best models on in-distribution datasets for both languages and an out-of-distribution dataset for Basque. LLaMA-Omni achieved 8.09% WER in Basque and 25.65% WER for Maltese on average across multiple test splits. The in-distribution results show that SpeechLM outperforms a fine-tuned ASR system under specific constraints, whereas it underperforms the baseline model on out-of-distribution Basque, indicating weaker overall robustness. We also find that a language-adapted LLM within SpeechLM improves in out-of-distribution settings when compared to the off-the-shelf LLM within SpeechLM.
%R 10.63317/2634e2pv97js
%U https://aclanthology.org/2026.speakable-1.14/
%U https://doi.org/10.63317/2634e2pv97js
%P 125-131
Markdown (Informal)
[SpeechLM for Automatic Speech Recognition in Low-resource Languages](https://aclanthology.org/2026.speakable-1.14/) (Riyadh et al., SPEAKABLE 2026)
ACL
- Md Abdur Razzaq Riyadh, Eneko Agirre, Eva Navas, and Claudia Borg. 2026. SpeechLM for Automatic Speech Recognition in Low-resource Languages. In Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026, pages 125–131, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).