TRADE augments multimodal Speech LLMs with a transducer branch for streaming ASR, reporting 6.71% WER offline and 8.40% streaming on the Open ASR Leaderboard from one checkpoint.
Fast conformer with lin- early scalable attention for efficient speech recognition, 2023
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
BEA-Dialogue+ expands the prior 85-hour Hungarian dialogue corpus to 200 hours via relaxed splits and demonstrates that SOT fine-tuning improves Whisper and FastConformer performance on word and character error metrics.
citing papers explorer
-
TRADE: Transducer-Augmented Decoder for Speech LLM
TRADE augments multimodal Speech LLMs with a transducer branch for streaming ASR, reporting 6.71% WER offline and 8.40% streaming on the Open ASR Leaderboard from one checkpoint.
-
Scaling Conversational Hungarian ASR: The BEA-Dialogue+ Corpus
BEA-Dialogue+ expands the prior 85-hour Hungarian dialogue corpus to 200 hours via relaxed splits and demonstrates that SOT fine-tuning improves Whisper and FastConformer performance on word and character error metrics.