Contrastive pre-training that aligns speech and text across all model layers beats ASR-based pre-training and, with 10% of task data, matches or exceeds specialized models on translation and question answering.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Contrastive Learning for Task-Independent SpeechLLM-Pretraining
Contrastive pre-training that aligns speech and text across all model layers beats ASR-based pre-training and, with 10% of task data, matches or exceeds specialized models on translation and question answering.