@inproceedings{amooie-etal-2026-improving,
title = "Improving Low-resource {ASR} Using Bilingual Fine-tuning with Language Identification: A Cross-linguistic Evaluation",
author = "Amooie, Reihaneh and
Hao, Yun and
de Vries, Wietse and
Dijkstra, Jelske and
Coler, Matt and
Wieling, Martijn",
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-1.15/",
doi = "10.63317/39snpbvopu74",
pages = "132--138",
abstract = "This study explores how bilingual fine-tuning affects automatic speech recognition (ASR) in low-resource languages. We evaluate this method across nine linguistically and geographically diverse language pairs, covering a range of language families and writing systems. To distinguish the two languages, during training, we pre-pend each input text with a language identification token. At inference, the model jointly predicts both the language and transcription from the speech input alone. As texts for which the language is incorrectly determined show low ASR performance, we also conduct a follow-up experiment in which the language identification token is provided both during training and inference. Our results show that bilingual fine-tuning can be beneficial when language identification accuracy is high, and that in cases where language identification performance is low, including the language identification token at inference helps to improve ASR performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="amooie-etal-2026-improving">
<titleInfo>
<title>Improving Low-resource ASR Using Bilingual Fine-tuning with Language Identification: A Cross-linguistic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reihaneh</namePart>
<namePart type="family">Amooie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wietse</namePart>
<namePart type="family">de Vries</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jelske</namePart>
<namePart type="family">Dijkstra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Coler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martijn</namePart>
<namePart type="family">Wieling</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>This study explores how bilingual fine-tuning affects automatic speech recognition (ASR) in low-resource languages. We evaluate this method across nine linguistically and geographically diverse language pairs, covering a range of language families and writing systems. To distinguish the two languages, during training, we pre-pend each input text with a language identification token. At inference, the model jointly predicts both the language and transcription from the speech input alone. As texts for which the language is incorrectly determined show low ASR performance, we also conduct a follow-up experiment in which the language identification token is provided both during training and inference. Our results show that bilingual fine-tuning can be beneficial when language identification accuracy is high, and that in cases where language identification performance is low, including the language identification token at inference helps to improve ASR performance.</abstract>
<identifier type="citekey">amooie-etal-2026-improving</identifier>
<identifier type="doi">10.63317/39snpbvopu74</identifier>
<location>
<url>https://aclanthology.org/2026.speakable-1.15/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>132</start>
<end>138</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Low-resource ASR Using Bilingual Fine-tuning with Language Identification: A Cross-linguistic Evaluation
%A Amooie, Reihaneh
%A Hao, Yun
%A de Vries, Wietse
%A Dijkstra, Jelske
%A Coler, Matt
%A Wieling, Martijn
%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 amooie-etal-2026-improving
%X This study explores how bilingual fine-tuning affects automatic speech recognition (ASR) in low-resource languages. We evaluate this method across nine linguistically and geographically diverse language pairs, covering a range of language families and writing systems. To distinguish the two languages, during training, we pre-pend each input text with a language identification token. At inference, the model jointly predicts both the language and transcription from the speech input alone. As texts for which the language is incorrectly determined show low ASR performance, we also conduct a follow-up experiment in which the language identification token is provided both during training and inference. Our results show that bilingual fine-tuning can be beneficial when language identification accuracy is high, and that in cases where language identification performance is low, including the language identification token at inference helps to improve ASR performance.
%R 10.63317/39snpbvopu74
%U https://aclanthology.org/2026.speakable-1.15/
%U https://doi.org/10.63317/39snpbvopu74
%P 132-138
Markdown (Informal)
[Improving Low-resource ASR Using Bilingual Fine-tuning with Language Identification: A Cross-linguistic Evaluation](https://aclanthology.org/2026.speakable-1.15/) (Amooie et al., SPEAKABLE 2026)
ACL
- Reihaneh Amooie, Yun Hao, Wietse de Vries, Jelske Dijkstra, Matt Coler, and Martijn Wieling. 2026. Improving Low-resource ASR Using Bilingual Fine-tuning with Language Identification: A Cross-linguistic Evaluation. In Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026, pages 132–138, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).