๐Ÿ“–
SyRA-CS: Synthetic-to-Real Adaptation for Code-Switched ASR with Meta-Learning
Fadel Thior, Ahmer Tabassum, Haania Siddiqui, Hanan Aldarmaki, Thamar Solorio

SyRA-CS: Synthetic-to-Real Adaptation for Code-Switched ASR with Meta-Learning

Science & Mathematics Published 2026 Verification Pending

Overview & Synopsis

Code-switched (CS) automatic speech recognition (ASR) remains difficult because real CS speech is scarce and synthetic speech does not fully match it. We investigate whether synthetic CS speech is more useful for learning an adaptation-friendly initialization than for ordinary continual fine-tuning. We propose SyRA-CS, a pair-specific synthetic-to-real adaptation framework based on Reptile meta-learning. For each language pair and pretrained model, we meta-train on the corresponding synthetic CS-FLEURS subset and then adapt using one hour of labeled real target speech. We evaluate four architectural settings: Encoder-CTC, FastConformer-RNN-T, Attention Encoder-Decoder (AED) and Speech-LLM. Experiments cover on Arabic-, French-, German-, and Hindi-English, against synthetic-only transfer, real-only fine-tuning, and continual fine-tuning. SyRA-CS improves over continual fine-tuning on WER in all 16 model-pair comparisons and on CER in 15 of 16, with relative macro WER reductions of 17.7% for XLS-R and 5.3-5.8% for the other three models. The gains hold across the tested models but vary in size across architectures, language pairs and metrics.

Indexed from repository: arXiv (arxiv.org)
Loading document from verified source...
Keyboard Shortcuts: ← / → for pages • + / - for zoom • 0 to fit width Powered by Mozilla PDF.js v3.11

Document Information

Document Title SyRA-CS: Synthetic-to-Real Adaptation for Code-Switched ASR with Meta-Learning
Author / Organization Fadel Thior, Ahmer Tabassum, Haania Siddiqui, Hanan Aldarmaki, Thamar Solorio
Subject & Discipline cs.CL
Categories Science & Mathematics
Publication Year 2026
License / Rights arXiv Open Access / Creative Commons
Resource Verification Listed PDF (Verification Pending)
Original Host Website arXiv (arxiv.org)
File Format application/pdf (Portable Document Format)
Language EN
Catalog ID DOC-263419
Original Source Link Visit Source Page on arxiv.org »