Introduces XLSR-Thai encoder, U-Align alignment, and Thai-SUP data pipeline to enable multitask speech understanding SLLMs for Thai.
Efficient Scaling for LLM-based ASR
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
JSTIP interleaves speech and text sequences during pretraining on 38k hours of ASR data to improve entity accuracy over ASR-only and simple joint-training baselines while matching performance from domain text.
citing papers explorer
No citing papers match the current filters.