A real-world continual learning benchmark for multilingual ASR built from 3,250 hours of Indian language speech shows that no current CL method performs consistently across language- and domain-incremental scenarios.
Prior work includes domain-specific ASR sub-models [19] and monolingual hybrid CTC-transformer adaptation [20], both fo- cusing on domain-incremental setups
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
NIRANTAR: Continual Learning with New Languages and Domains on Real-world Speech Data
A real-world continual learning benchmark for multilingual ASR built from 3,250 hours of Indian language speech shows that no current CL method performs consistently across language- and domain-incremental scenarios.