Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Talafha, Bashar, Alhassan, Amin Abu, Abdul-Mageed, Muhammad
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.18774
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909986281488384
author Talafha, Bashar
Alhassan, Amin Abu
Abdul-Mageed, Muhammad
author_facet Talafha, Bashar
Alhassan, Amin Abu
Abdul-Mageed, Muhammad
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18774
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Zero-Shot Context-Aware ASR for Diverse Arabic Varieties
Talafha, Bashar
Alhassan, Amin Abu
Abdul-Mageed, Muhammad
Computation and Language
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.
title Zero-Shot Context-Aware ASR for Diverse Arabic Varieties
topic Computation and Language
url https://arxiv.org/abs/2511.18774