@inproceedings{saleem-etal-2026-development,
title = "Development of {B}urushaski Speech - {E}nglish Text Translation Dataset",
author = "Saleem, Tauqeer and
Samad, Abdul and
Nasir, Azkaa and
Mansoor, Adina Adnan and
Faisal, Fatima and
Yousuf, Mahrukh",
editor = "Sarveswaran, Kengatharaiyer and
Vaidya, Ashwini",
booktitle = "Proceedings of the Second workshop on Challenges in Processing {S}outh {A}sian Languages ({CH}i{PSAL}2026)",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.chipsal-1.2/",
doi = "10.63317/3ujn9xefj6ca",
pages = "9--17",
abstract = "Burushaski is a language isolate spoken in northern Pakistan with a predominantly oral tradition, limited standardized orthography, and virtually no existing speech technology infrastructure. These characteristics make conventional text-centric NLP pipelines unsuitable and position speech data collection as the primary scientific challenge. This paper introduces an audio-first, linguistically informed methodology for developing a Burushaski{--}English speech translation resource. Rather than prioritizing model architecture, we focus on principled corpus design tailored to the language{'}s morphological complexity, ergative-absolutive alignment, and four-gender agreement system. The dataset combines structured elicitation targeting high-frequency and morphologically diverse constructions, functional and formulaic speech, and oral narratives that capture discourse-level phenomena. We describe the design of a custom data collection application, community-embedded crowdsourcing strategy, and translation-aligned workflow for generating parallel speech{--}English data. The resulting pilot corpus comprises approximately 10 hours of curated audio from 42 speakers across controlled and naturalistic settings. While we present the results of preliminary translation experiments using Whisper, the primary contribution of this work is methodological: a scalable framework for speech-first corpus development in morphologically rich, under-resourced, and predominantly oral languages. We argue that for languages lacking stable orthography and large textual corpora, data design, not model selection constitutes the central research problem"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saleem-etal-2026-development">
<titleInfo>
<title>Development of Burushaski Speech - English Text Translation Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tauqeer</namePart>
<namePart type="family">Saleem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdul</namePart>
<namePart type="family">Samad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azkaa</namePart>
<namePart type="family">Nasir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adina</namePart>
<namePart type="given">Adnan</namePart>
<namePart type="family">Mansoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fatima</namePart>
<namePart type="family">Faisal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahrukh</namePart>
<namePart type="family">Yousuf</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 the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kengatharaiyer</namePart>
<namePart type="family">Sarveswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwini</namePart>
<namePart type="family">Vaidya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Burushaski is a language isolate spoken in northern Pakistan with a predominantly oral tradition, limited standardized orthography, and virtually no existing speech technology infrastructure. These characteristics make conventional text-centric NLP pipelines unsuitable and position speech data collection as the primary scientific challenge. This paper introduces an audio-first, linguistically informed methodology for developing a Burushaski–English speech translation resource. Rather than prioritizing model architecture, we focus on principled corpus design tailored to the language’s morphological complexity, ergative-absolutive alignment, and four-gender agreement system. The dataset combines structured elicitation targeting high-frequency and morphologically diverse constructions, functional and formulaic speech, and oral narratives that capture discourse-level phenomena. We describe the design of a custom data collection application, community-embedded crowdsourcing strategy, and translation-aligned workflow for generating parallel speech–English data. The resulting pilot corpus comprises approximately 10 hours of curated audio from 42 speakers across controlled and naturalistic settings. While we present the results of preliminary translation experiments using Whisper, the primary contribution of this work is methodological: a scalable framework for speech-first corpus development in morphologically rich, under-resourced, and predominantly oral languages. We argue that for languages lacking stable orthography and large textual corpora, data design, not model selection constitutes the central research problem</abstract>
<identifier type="citekey">saleem-etal-2026-development</identifier>
<identifier type="doi">10.63317/3ujn9xefj6ca</identifier>
<location>
<url>https://aclanthology.org/2026.chipsal-1.2/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>9</start>
<end>17</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Development of Burushaski Speech - English Text Translation Dataset
%A Saleem, Tauqeer
%A Samad, Abdul
%A Nasir, Azkaa
%A Mansoor, Adina Adnan
%A Faisal, Fatima
%A Yousuf, Mahrukh
%Y Sarveswaran, Kengatharaiyer
%Y Vaidya, Ashwini
%S Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F saleem-etal-2026-development
%X Burushaski is a language isolate spoken in northern Pakistan with a predominantly oral tradition, limited standardized orthography, and virtually no existing speech technology infrastructure. These characteristics make conventional text-centric NLP pipelines unsuitable and position speech data collection as the primary scientific challenge. This paper introduces an audio-first, linguistically informed methodology for developing a Burushaski–English speech translation resource. Rather than prioritizing model architecture, we focus on principled corpus design tailored to the language’s morphological complexity, ergative-absolutive alignment, and four-gender agreement system. The dataset combines structured elicitation targeting high-frequency and morphologically diverse constructions, functional and formulaic speech, and oral narratives that capture discourse-level phenomena. We describe the design of a custom data collection application, community-embedded crowdsourcing strategy, and translation-aligned workflow for generating parallel speech–English data. The resulting pilot corpus comprises approximately 10 hours of curated audio from 42 speakers across controlled and naturalistic settings. While we present the results of preliminary translation experiments using Whisper, the primary contribution of this work is methodological: a scalable framework for speech-first corpus development in morphologically rich, under-resourced, and predominantly oral languages. We argue that for languages lacking stable orthography and large textual corpora, data design, not model selection constitutes the central research problem
%R 10.63317/3ujn9xefj6ca
%U https://aclanthology.org/2026.chipsal-1.2/
%U https://doi.org/10.63317/3ujn9xefj6ca
%P 9-17
Markdown (Informal)
[Development of Burushaski Speech - English Text Translation Dataset](https://aclanthology.org/2026.chipsal-1.2/) (Saleem et al., CHiPSAL 2026)
ACL
- Tauqeer Saleem, Abdul Samad, Azkaa Nasir, Adina Adnan Mansoor, Fatima Faisal, and Mahrukh Yousuf. 2026. Development of Burushaski Speech - English Text Translation Dataset. In Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026), pages 9–17, Palma de Mallorca, Spain. ELRA Language Resources Association (ELRA).