@inproceedings{marilign-etal-2026-teleasr,
title = "{T}ele{ASR}-{A}mharic: A Benchmark for Robust {A}mharic {ASR} in Realistic Telecommunication Conditions",
author = "Marilign, Dagnachew Mekonnen and
Molero, Enrique and
Haile, Abrham and
Powell, Louis and
Azime, Israel Abebe",
editor = {Chen, Nancy F. and
Chen, Yiming and
Gao, Xiaoxue and
Li, Haizhou and
Schuller, Bj{\"o}rn and
Sisman, Berrak and
Yue, Xianghu},
booktitle = "Proceedings of the Workshop on Secure, Safe, and Privacy-Preserving Speech and Audio {AI} ({T}rust{A}udio 2026)",
month = nov,
year = "2026",
address = "Hengqin, Zhuhai, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.trustaudio-1.2/",
pages = "11--23",
ISBN = "979-8-89176-452-1",
abstract = "The real-world usability of ASR models remains challenging, particularly for low-resource languages, where existing speech resources are often collected in clean studio environments. In this work, we introduce TeleASR-Amharic, a benchmark for evaluating Amharic ASR under various acoustic and telecommunication conditions. We analyze the major degradations observed in real telecommunications recordings and develop a benchmark that covers multiple channel conditions, environmental disturbances, and telecom-domain variations. Our results show that telecommunication degradation can substantially reduce recognition performance, making even high-performing ASR models impractical under severe conditions. For example, the WER of the best-performing model{'}s increases from 0.23 to 0.79 under severe telecommunication degradation, corresponding to a relative increase of 243{\%} in recognition errors. We further investigate the effects of different noise and channel distortions and show that scaling training data and applying carefully designed telecommunication-aware augmentation substantially improve robustness. In particular, our best training configuration achieves a 23.6{\%} relative WER reduction under extreme noise conditions. Together with the release of our telecommunications-domain data, these findings provide a reproducible benchmark for measuring progress in Amharic ASR while highlighting open challenges in developing robust speech technologies for real-world deployment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marilign-etal-2026-teleasr">
<titleInfo>
<title>TeleASR-Amharic: A Benchmark for Robust Amharic ASR in Realistic Telecommunication Conditions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dagnachew</namePart>
<namePart type="given">Mekonnen</namePart>
<namePart type="family">Marilign</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrique</namePart>
<namePart type="family">Molero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abrham</namePart>
<namePart type="family">Haile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louis</namePart>
<namePart type="family">Powell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Israel</namePart>
<namePart type="given">Abebe</namePart>
<namePart type="family">Azime</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Secure, Safe, and Privacy-Preserving Speech and Audio AI (TrustAudio 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoxue</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haizhou</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Björn</namePart>
<namePart type="family">Schuller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berrak</namePart>
<namePart type="family">Sisman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianghu</namePart>
<namePart type="family">Yue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, Zhuhai, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-452-1</identifier>
</relatedItem>
<abstract>The real-world usability of ASR models remains challenging, particularly for low-resource languages, where existing speech resources are often collected in clean studio environments. In this work, we introduce TeleASR-Amharic, a benchmark for evaluating Amharic ASR under various acoustic and telecommunication conditions. We analyze the major degradations observed in real telecommunications recordings and develop a benchmark that covers multiple channel conditions, environmental disturbances, and telecom-domain variations. Our results show that telecommunication degradation can substantially reduce recognition performance, making even high-performing ASR models impractical under severe conditions. For example, the WER of the best-performing model’s increases from 0.23 to 0.79 under severe telecommunication degradation, corresponding to a relative increase of 243% in recognition errors. We further investigate the effects of different noise and channel distortions and show that scaling training data and applying carefully designed telecommunication-aware augmentation substantially improve robustness. In particular, our best training configuration achieves a 23.6% relative WER reduction under extreme noise conditions. Together with the release of our telecommunications-domain data, these findings provide a reproducible benchmark for measuring progress in Amharic ASR while highlighting open challenges in developing robust speech technologies for real-world deployment.</abstract>
<identifier type="citekey">marilign-etal-2026-teleasr</identifier>
<location>
<url>https://aclanthology.org/2026.trustaudio-1.2/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>11</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TeleASR-Amharic: A Benchmark for Robust Amharic ASR in Realistic Telecommunication Conditions
%A Marilign, Dagnachew Mekonnen
%A Molero, Enrique
%A Haile, Abrham
%A Powell, Louis
%A Azime, Israel Abebe
%Y Chen, Nancy F.
%Y Chen, Yiming
%Y Gao, Xiaoxue
%Y Li, Haizhou
%Y Schuller, Björn
%Y Sisman, Berrak
%Y Yue, Xianghu
%S Proceedings of the Workshop on Secure, Safe, and Privacy-Preserving Speech and Audio AI (TrustAudio 2026)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, Zhuhai, China
%@ 979-8-89176-452-1
%F marilign-etal-2026-teleasr
%X The real-world usability of ASR models remains challenging, particularly for low-resource languages, where existing speech resources are often collected in clean studio environments. In this work, we introduce TeleASR-Amharic, a benchmark for evaluating Amharic ASR under various acoustic and telecommunication conditions. We analyze the major degradations observed in real telecommunications recordings and develop a benchmark that covers multiple channel conditions, environmental disturbances, and telecom-domain variations. Our results show that telecommunication degradation can substantially reduce recognition performance, making even high-performing ASR models impractical under severe conditions. For example, the WER of the best-performing model’s increases from 0.23 to 0.79 under severe telecommunication degradation, corresponding to a relative increase of 243% in recognition errors. We further investigate the effects of different noise and channel distortions and show that scaling training data and applying carefully designed telecommunication-aware augmentation substantially improve robustness. In particular, our best training configuration achieves a 23.6% relative WER reduction under extreme noise conditions. Together with the release of our telecommunications-domain data, these findings provide a reproducible benchmark for measuring progress in Amharic ASR while highlighting open challenges in developing robust speech technologies for real-world deployment.
%U https://aclanthology.org/2026.trustaudio-1.2/
%P 11-23
Markdown (Informal)
[TeleASR-Amharic: A Benchmark for Robust Amharic ASR in Realistic Telecommunication Conditions](https://aclanthology.org/2026.trustaudio-1.2/) (Marilign et al., TrustAudio 2026)
ACL
- Dagnachew Mekonnen Marilign, Enrique Molero, Abrham Haile, Louis Powell, and Israel Abebe Azime. 2026. TeleASR-Amharic: A Benchmark for Robust Amharic ASR in Realistic Telecommunication Conditions. In Proceedings of the Workshop on Secure, Safe, and Privacy-Preserving Speech and Audio AI (TrustAudio 2026), pages 11–23, Hengqin, Zhuhai, China. Association for Computational Linguistics.