Paper
Ethio-ASR: Joint Multilingual Speech Recognition and Language Identification for Ethiopian Languages
Authors
Badr M. Abdullah, Israel Abebe Azime, Atnafu Lambebo Tonja, Jesujoba O. Alabi, Abel Mulat Alemu, Eyob G. Hagos, Bontu Fufa Balcha, Mulubrhan A. Nerea, Debela Desalegn Yadeta, Dagnachew Mekonnen Marilign, Amanuel Temesgen Fentahun, Tadesse Kebede, Israel D. Gebru, Michael Melese Woldeyohannis, Walelign Tewabe Sewunetie, Bernd Möbius, Dietrich Klakow
Abstract
We present Ethio-ASR, a suite of multilingual CTC-based automatic speech recognition (ASR) models jointly trained on five Ethiopian languages: Amharic, Tigrinya, Oromo, Sidaama, and Wolaytta. These languages belong to the Semitic, Cushitic, and Omotic branches of the Afroasiatic family, and remain severely underrepresented in speech technology despite being spoken by the vast majority of Ethiopia's population. We train our models on the recently released WAXAL corpus using several pre-trained speech encoders and evaluate against strong multilingual baselines, including OmniASR. Our best model achieves an average WER of 30.48% on the WAXAL test set, outperforming the best OmniASR model with substantially fewer parameters. We further provide a comprehensive analysis of gender bias, the contribution of vowel length and consonant gemination to ASR errors, and the training dynamics of multilingual CTC models. Our models and codebase are publicly available to the research community.
Metadata
Related papers
Fractal universe and quantum gravity made simple
Fabio Briscese, Gianluca Calcagni • 2026-03-25
POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan
Marta Moscati, Muhammad Saad Saeed, Marina Zanoni, Mubashir Noman, Rohan Kuma... • 2026-03-25
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan • 2026-03-25
Orientation Reconstruction of Proteins using Coulomb Explosions
Tomas André, Alfredo Bellisario, Nicusor Timneanu, Carl Caleman • 2026-03-25
The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series
Jan Hemmerling, Marcel Schwieder, Philippe Rufin, Leon-Friedrich Thomas, Mire... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.23654v1</id>\n <title>Ethio-ASR: Joint Multilingual Speech Recognition and Language Identification for Ethiopian Languages</title>\n <updated>2026-03-24T18:55:45Z</updated>\n <link href='https://arxiv.org/abs/2603.23654v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.23654v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>We present Ethio-ASR, a suite of multilingual CTC-based automatic speech recognition (ASR) models jointly trained on five Ethiopian languages: Amharic, Tigrinya, Oromo, Sidaama, and Wolaytta. These languages belong to the Semitic, Cushitic, and Omotic branches of the Afroasiatic family, and remain severely underrepresented in speech technology despite being spoken by the vast majority of Ethiopia's population. We train our models on the recently released WAXAL corpus using several pre-trained speech encoders and evaluate against strong multilingual baselines, including OmniASR. Our best model achieves an average WER of 30.48% on the WAXAL test set, outperforming the best OmniASR model with substantially fewer parameters. We further provide a comprehensive analysis of gender bias, the contribution of vowel length and consonant gemination to ASR errors, and the training dynamics of multilingual CTC models. Our models and codebase are publicly available to the research community.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n <published>2026-03-24T18:55:45Z</published>\n <arxiv:comment>Preprint (under review)</arxiv:comment>\n <arxiv:primary_category term='cs.CL'/>\n <author>\n <name>Badr M. Abdullah</name>\n </author>\n <author>\n <name>Israel Abebe Azime</name>\n </author>\n <author>\n <name>Atnafu Lambebo Tonja</name>\n </author>\n <author>\n <name>Jesujoba O. Alabi</name>\n </author>\n <author>\n <name>Abel Mulat Alemu</name>\n </author>\n <author>\n <name>Eyob G. Hagos</name>\n </author>\n <author>\n <name>Bontu Fufa Balcha</name>\n </author>\n <author>\n <name>Mulubrhan A. Nerea</name>\n </author>\n <author>\n <name>Debela Desalegn Yadeta</name>\n </author>\n <author>\n <name>Dagnachew Mekonnen Marilign</name>\n </author>\n <author>\n <name>Amanuel Temesgen Fentahun</name>\n </author>\n <author>\n <name>Tadesse Kebede</name>\n </author>\n <author>\n <name>Israel D. Gebru</name>\n </author>\n <author>\n <name>Michael Melese Woldeyohannis</name>\n </author>\n <author>\n <name>Walelign Tewabe Sewunetie</name>\n </author>\n <author>\n <name>Bernd Möbius</name>\n </author>\n <author>\n <name>Dietrich Klakow</name>\n </author>\n </entry>"
}