# Zero-Shot Context-Aware ASR for Diverse Arabic Varieties

arXiv: https://arxiv.org/abs/2511.18774 · HTML: https://mlsanity.com/paper/2511.18774/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 24 Nov 2025.

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

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [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)
- [XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model](https://mlsanity.com/paper/2406.04904/) (2024)
- [SeamlessM4T: Massively Multilingual & Multimodal Machine Translation](https://mlsanity.com/paper/2308.11596/) (2023)
- [Speech Recognition Challenge in the Wild: Arabic MGB-3](https://mlsanity.com/paper/1709.07276/) (2017)
- [Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST](https://mlsanity.com/paper/2509.14128/) (2025)
- [Can Whisper perform speech-based in-context learning?](https://mlsanity.com/paper/2309.07081/) (2023)
- [Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages](https://mlsanity.com/paper/2511.09690/) (2025)
- [The MGB-2 Challenge: Arabic Multi-Dialect Broadcast Media Recognition](https://mlsanity.com/paper/1609.05625/) (2016)
- [N-Shot Benchmarking of Whisper on Diverse Arabic Speech Recognition](https://mlsanity.com/paper/2306.02902/) (2023)
- [Improving Domain-Specific ASR with LLM-Generated Contextual Descriptions](https://mlsanity.com/paper/2407.17874/) (2024)
- [To Distill or Not to Distill? On the Robustness of Robust Knowledge Distillation](https://mlsanity.com/paper/2406.04512/) (2024)
- [uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation in Low-Data Regimes](https://mlsanity.com/paper/2407.01257/) (2024)
- [Retrieval-Augmented Speech Recognition Approach for Domain Challenges](https://mlsanity.com/paper/2502.15264/) (2025)
- [Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognition](https://mlsanity.com/paper/2510.19471/) (2025)

## Abstract (arXiv)

Zero-shot ASR for Arabic remains challenging: while multilingual models perform well on Modern Standard Arabic (MSA), error rates rise sharply on dialectal and accented speech due to linguistic mismatch and scarce labeled data. We study context-aware decoding as a lightweight test-time adaptation paradigm that conditions inference on external side information without parameter updates. For promptable encoder-decoder ASR (e.g., Whisper), we incorporate context through (i) decoder prompting with first-pass hypotheses and (ii) encoder/decoder prefixing with retrieved speech-text exemplars, complemented by simple prompt reordering and optional speaker-matched synthetic exemplars to improve robustness in informal and multi-speaker settings. To extend contextual adaptation beyond promptable architectures, we introduce proxy-guided n-best selection for CTC ASR: given one or more external proxy hypotheses, we select from a model's n-best list by minimizing text-level distance to the proxies, enabling contextual inference without direct prompting. Across ten Arabic conditions spanning MSA, accented MSA, and multiple dialects, context-aware decoding yields average relative WER reductions of 22.29% on MSA, 20.54 on accented MSA, and 9.15% on dialectal Arabic. For CTC models, proxy-guided selection reduces WER by 15.6% relative on MSA and recovers a substantial fraction of oracle n-best gains, demonstrating that context-aware inference generalizes beyond encoder-decoder ASR.