# Ethio-ASR: Joint Multilingual Speech Recognition and Language Identification for Ethiopian Languages

arXiv: https://arxiv.org/abs/2603.23654 · HTML: https://mlsanity.com/paper/2603.23654/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 44 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 19 of 19)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Seamless: Multilingual Expressive and Streaming Speech Translation](https://mlsanity.com/paper/2312.05187/) (2023)
- [Quantifying Bias in Automatic Speech Recognition](https://mlsanity.com/paper/2103.15122/) (2021)
- [OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification](https://mlsanity.com/paper/2402.12654/) (2024)
- [Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages](https://mlsanity.com/paper/2511.09690/) (2025)
- [Hey ASR System! Why Aren't You More Inclusive? Automatic Speech Recognition Systems' Bias and Proposed Bias Mitigation Techniques. A Literature Review](https://mlsanity.com/paper/2211.09511/) (2022)
- [AfriHuBERT: A self-supervised speech representation model for African languages](https://mlsanity.com/paper/2409.20201/) (2024)
- [Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead](https://mlsanity.com/paper/2505.21315/) (2025)
- [Data Quality Issues in Multilingual Speech Datasets: The Need for Sociolinguistic Awareness and Proactive Language Planning](https://mlsanity.com/paper/2506.17525/) (2025)
- [WAXAL: A Large-Scale Multilingual African Language Speech Corpus](https://mlsanity.com/paper/2602.02734/) (2026)
- [Automatic Speech Recognition for African Low-Resource Languages: Challenges and Future Directions](https://mlsanity.com/paper/2505.11690/) (2025)
- [Semantically Corrected Amharic Automatic Speech Recognition](https://mlsanity.com/paper/2404.13362/) (2024)
- [Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo Language](https://mlsanity.com/paper/2502.00421/) (2025)
- [CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition](https://mlsanity.com/paper/2502.01777/) (2025)
- [A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the Ge'ez Script](https://mlsanity.com/paper/2507.15142/) (2025)

## Built on by (most cited first, 2 of 2)

- [WAXAL-NET: Finetuned Edge ASR Across 19 African Languages](https://mlsanity.com/paper/2606.02375/) (2026)
- [Offline AI Modules: Voice-First Offline Architecture, Hardware Reference Stack, Quantization and Benchmarking](https://mlsanity.com/paper/2610.07026/) (2026)

## Abstract (arXiv)

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.