Proposes Bayesian factorized adaptation for multilingual ASR to handle code-switching, reporting 32.87% fewer errors on switched words and 5.31% better overall WER while preserving monolingual accuracy with small synthetic data.
Efficient weight factorization for multilingual speech recognition,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
KIT's IWSLT submission uses segment concatenation, LLM label generation and cross-lingual translation to create >1M long-form training instances and shows that likelihood re-ranking harms semantic tasks unless combined with Minimum Bayes Risk decoding.
citing papers explorer
-
Adding Robust Code-Switching Capabilities to High Performance Multilingual ASR
Proposes Bayesian factorized adaptation for multilingual ASR to handle code-switching, reporting 32.87% fewer errors on switched words and 5.31% better overall WER while preserving monolingual accuracy with small synthetic data.
-
Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026
KIT's IWSLT submission uses segment concatenation, LLM label generation and cross-lingual translation to create >1M long-form training instances and shows that likelihood re-ranking harms semantic tasks unless combined with Minimum Bayes Risk decoding.