Domain Adaptation with Incremental Learning for Code-Switching ASR Performance

Automatic Speech Recognition (ASR) has become a key technology for human--AI interaction. However, code-switching ASR (CS-ASR) remains particularly challenging due to the severe scarcity of multilingual CS speech resources across diverse language pairs. Existing approaches primarily improve CS-ASR performance through synthetic CS speech generation or pair-specific fine-tuning on limited bilingual datasets. Nevertheless, these approaches face an inherent scalability limitation, as support for CS must be developed separately for language pairs whose number grows combinatorially with the number o

Research goal: To what extent does domain adaptation with incremental learning improve code-switching ASR performance on unseen language pairs while preserving monolingual WER, as evaluated on LibriMix and CoSwDA datasets?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.