@inproceedings{mandal-etal-2025-whispering,
title = "Whispering in Ol Chiki: Cross-Lingual Transfer Learning for {S}antali Speech Recognition",
author = "Mandal, Atanu and
Ghosh, Madhusudan and
Maiti, Pratick and
Naskar, Sudip Kumar",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-ijcnlp.16/",
pages = "269--278",
ISBN = "979-8-89176-303-6",
abstract = "India, a country with a large population, possesses two official and twenty-two scheduled languages, making it the most linguistically diverse nation. Despite being one of the scheduled languages, Santali remains a low-resource language. Although Ol Chiki is recognized as the official script for Santali, many continue to use Bengali, Devanagari, Odia, and Roman scripts. In tribute to the upcoming centennial anniversary of the Ol Chiki script, we present an Automatic Speech Recognition for Santali in the Ol Chiki script. Our approach involves cross-lingual transfer learning by utilizing the Whisper framework pre-trained in Bengali and Hindi on the Santali language, using Ol Chiki script transcriptions. With the adoption of the Bengali pre-trained framework, we achieved a Word Error Rate (WER) score of 28.47{\%}, whereas the adaptation of the Hindi pre-trained framework resulted in a score of 34.50{\%} WER. These outcomes were obtained using the Whisper Small framework."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mandal-etal-2025-whispering">
<titleInfo>
<title>Whispering in Ol Chiki: Cross-Lingual Transfer Learning for Santali Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atanu</namePart>
<namePart type="family">Mandal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madhusudan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pratick</namePart>
<namePart type="family">Maiti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudip</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Naskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</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">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-303-6</identifier>
</relatedItem>
<abstract>India, a country with a large population, possesses two official and twenty-two scheduled languages, making it the most linguistically diverse nation. Despite being one of the scheduled languages, Santali remains a low-resource language. Although Ol Chiki is recognized as the official script for Santali, many continue to use Bengali, Devanagari, Odia, and Roman scripts. In tribute to the upcoming centennial anniversary of the Ol Chiki script, we present an Automatic Speech Recognition for Santali in the Ol Chiki script. Our approach involves cross-lingual transfer learning by utilizing the Whisper framework pre-trained in Bengali and Hindi on the Santali language, using Ol Chiki script transcriptions. With the adoption of the Bengali pre-trained framework, we achieved a Word Error Rate (WER) score of 28.47%, whereas the adaptation of the Hindi pre-trained framework resulted in a score of 34.50% WER. These outcomes were obtained using the Whisper Small framework.</abstract>
<identifier type="citekey">mandal-etal-2025-whispering</identifier>
<location>
<url>https://aclanthology.org/2025.findings-ijcnlp.16/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>269</start>
<end>278</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Whispering in Ol Chiki: Cross-Lingual Transfer Learning for Santali Speech Recognition
%A Mandal, Atanu
%A Ghosh, Madhusudan
%A Maiti, Pratick
%A Naskar, Sudip Kumar
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-303-6
%F mandal-etal-2025-whispering
%X India, a country with a large population, possesses two official and twenty-two scheduled languages, making it the most linguistically diverse nation. Despite being one of the scheduled languages, Santali remains a low-resource language. Although Ol Chiki is recognized as the official script for Santali, many continue to use Bengali, Devanagari, Odia, and Roman scripts. In tribute to the upcoming centennial anniversary of the Ol Chiki script, we present an Automatic Speech Recognition for Santali in the Ol Chiki script. Our approach involves cross-lingual transfer learning by utilizing the Whisper framework pre-trained in Bengali and Hindi on the Santali language, using Ol Chiki script transcriptions. With the adoption of the Bengali pre-trained framework, we achieved a Word Error Rate (WER) score of 28.47%, whereas the adaptation of the Hindi pre-trained framework resulted in a score of 34.50% WER. These outcomes were obtained using the Whisper Small framework.
%U https://aclanthology.org/2025.findings-ijcnlp.16/
%P 269-278
Markdown (Informal)
[Whispering in Ol Chiki: Cross-Lingual Transfer Learning for Santali Speech Recognition](https://aclanthology.org/2025.findings-ijcnlp.16/) (Mandal et al., Findings 2025)
ACL
- Atanu Mandal, Madhusudan Ghosh, Pratick Maiti, and Sudip Kumar Naskar. 2025. Whispering in Ol Chiki: Cross-Lingual Transfer Learning for Santali Speech Recognition. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 269–278, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.