Serialized CTC outputs from auxiliary branches, used as LLM prompts, improve LLM-based multi-talker ASR WER on Libri2Mix and Libri3Mix.
End-to-end monaural multi-speaker ASR system without pretraining,
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
-
Serialized Output Prompting for Large Language Model-based Multi-Talker Speech Recognition
Serialized CTC outputs from auxiliary branches, used as LLM prompts, improve LLM-based multi-talker ASR WER on Libri2Mix and Libri3Mix.