SpecASR accelerates LLM-based ASR by 3.04x-3.79x over autoregressive decoding using adaptive draft lengths, draft token recycling, and sparse token trees, but the speedups are simulated from Whisper proxy models rather than measured on LLM-based ASR systems.
On decoder-only architecture for speech-to-text and large language model integration,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
REJECT 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding
SpecASR accelerates LLM-based ASR by 3.04x-3.79x over autoregressive decoding using adaptive draft lengths, draft token recycling, and sparse token trees, but the speedups are simulated from Whisper proxy models rather than measured on LLM-based ASR systems.