@inproceedings{geng-etal-2025-supporting,
title = "Supporting {SEN{\'C}O{\={T}}EN} Language Documentation Efforts with Automatic Speech Recognition",
author = "Geng, Mengzhe and
Littell, Patrick and
Pine, Aidan and
Pen{\'a}{\'c} and
Tessier, Marc and
Kuhn, Roland",
editor = "Lachler, Jordan and
Agyapong, Godfred and
Arppe, Antti and
Moeller, Sarah and
Chaudhary, Aditi and
Rijhwani, Shruti and
Rosenblum, Daisy",
booktitle = "Proceedings of the Eight Workshop on the Use of Computational Methods in the Study of Endangered Languages",
month = mar,
year = "2025",
address = "Honolulu, Hawaii, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.computel-main.4/",
pages = "29--39",
abstract = "The SEN{\'C}O{\={T}}EN language, spoken on the Saanich peninsula of southern Vancouver Island, is in the midst of vigorous language revitalization efforts to turn the tide of language loss as a result of colonial language policies. To support these on-the-ground efforts, the community is turning to digital technology. Automatic Speech Recognition (ASR) technology holds great promise for accelerating language documentation and the creation of educational resources. However, developing ASR systems for SENCOTEN is challenging due to limited data and significant vocabulary variation from its polysynthetic structure and stress-driven metathesis. To address these challenges, we propose an ASR-driven documentation pipeline that leverages augmented speech data from a text-to-speech (TTS) system and cross-lingual transfer learning with Speech Foundation Models (SFMs). An n-gram language model is also incorporated via shallow fusion or n-best restoring to maximize the use of available data. Experiments on the SENCOTEN dataset show aword error rate (WER) of 19.34{\%} and a character error rate (CER) of 5.09{\%} on the test set with a 57.02{\%} out-of-vocabulary (OOV) rate. After filtering minor cedilla-related errors,WER improves to 14.32{\%} (26.48{\%} on unseen words) and CER to 3.45{\%}, demonstrating the potential of our ASR-driven pipeline to support SENCOTEN language documentation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="geng-etal-2025-supporting">
<titleInfo>
<title>Supporting SENĆO\=TEN Language Documentation Efforts with Automatic Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mengzhe</namePart>
<namePart type="family">Geng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Littell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aidan</namePart>
<namePart type="family">Pine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Penáć</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Tessier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roland</namePart>
<namePart type="family">Kuhn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eight Workshop on the Use of Computational Methods in the Study of Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Lachler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Godfred</namePart>
<namePart type="family">Agyapong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antti</namePart>
<namePart type="family">Arppe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Moeller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditi</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisy</namePart>
<namePart type="family">Rosenblum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Honolulu, Hawaii, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The SENĆO\=TEN language, spoken on the Saanich peninsula of southern Vancouver Island, is in the midst of vigorous language revitalization efforts to turn the tide of language loss as a result of colonial language policies. To support these on-the-ground efforts, the community is turning to digital technology. Automatic Speech Recognition (ASR) technology holds great promise for accelerating language documentation and the creation of educational resources. However, developing ASR systems for SENCOTEN is challenging due to limited data and significant vocabulary variation from its polysynthetic structure and stress-driven metathesis. To address these challenges, we propose an ASR-driven documentation pipeline that leverages augmented speech data from a text-to-speech (TTS) system and cross-lingual transfer learning with Speech Foundation Models (SFMs). An n-gram language model is also incorporated via shallow fusion or n-best restoring to maximize the use of available data. Experiments on the SENCOTEN dataset show aword error rate (WER) of 19.34% and a character error rate (CER) of 5.09% on the test set with a 57.02% out-of-vocabulary (OOV) rate. After filtering minor cedilla-related errors,WER improves to 14.32% (26.48% on unseen words) and CER to 3.45%, demonstrating the potential of our ASR-driven pipeline to support SENCOTEN language documentation.</abstract>
<identifier type="citekey">geng-etal-2025-supporting</identifier>
<location>
<url>https://aclanthology.org/2025.computel-main.4/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>29</start>
<end>39</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Supporting SENĆO\=TEN Language Documentation Efforts with Automatic Speech Recognition
%A Geng, Mengzhe
%A Littell, Patrick
%A Pine, Aidan
%A Tessier, Marc
%A Kuhn, Roland
%Y Lachler, Jordan
%Y Agyapong, Godfred
%Y Arppe, Antti
%Y Moeller, Sarah
%Y Chaudhary, Aditi
%Y Rijhwani, Shruti
%Y Rosenblum, Daisy
%A Penáć
%S Proceedings of the Eight Workshop on the Use of Computational Methods in the Study of Endangered Languages
%D 2025
%8 March
%I Association for Computational Linguistics
%C Honolulu, Hawaii, USA
%F geng-etal-2025-supporting
%X The SENĆO\=TEN language, spoken on the Saanich peninsula of southern Vancouver Island, is in the midst of vigorous language revitalization efforts to turn the tide of language loss as a result of colonial language policies. To support these on-the-ground efforts, the community is turning to digital technology. Automatic Speech Recognition (ASR) technology holds great promise for accelerating language documentation and the creation of educational resources. However, developing ASR systems for SENCOTEN is challenging due to limited data and significant vocabulary variation from its polysynthetic structure and stress-driven metathesis. To address these challenges, we propose an ASR-driven documentation pipeline that leverages augmented speech data from a text-to-speech (TTS) system and cross-lingual transfer learning with Speech Foundation Models (SFMs). An n-gram language model is also incorporated via shallow fusion or n-best restoring to maximize the use of available data. Experiments on the SENCOTEN dataset show aword error rate (WER) of 19.34% and a character error rate (CER) of 5.09% on the test set with a 57.02% out-of-vocabulary (OOV) rate. After filtering minor cedilla-related errors,WER improves to 14.32% (26.48% on unseen words) and CER to 3.45%, demonstrating the potential of our ASR-driven pipeline to support SENCOTEN language documentation.
%U https://aclanthology.org/2025.computel-main.4/
%P 29-39
Markdown (Informal)
[Supporting SENĆOŦEN Language Documentation Efforts with Automatic Speech Recognition](https://aclanthology.org/2025.computel-main.4/) (Geng et al., ComputEL 2025)
ACL