A multi-stage training method for LLM-based ASR uses new entropy allocation metrics to achieve competitive benchmark performance with 2.3B parameters while mitigating hallucinations via better encoder-LLM decoupling.
Cr-ctc: Consistency regularization on ctc for improved speech recognition.arXiv preprint arXiv:2410.05101
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
eess.AS 3years
2026 3verdicts
UNVERDICTED 3roles
method 1polarities
use method 1representative citing papers
MedASR is an open-source 105M-parameter ASR model achieving 58% relative WER reduction versus Whisper Large-v3 on medical dictation.
NIM4-ASR delivers SOTA ASR performance on public benchmarks using a 2.3B-parameter LLM with multi-stage training, real-time streaming, and million-scale hotword customization via RAG.
citing papers explorer
-
Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
A multi-stage training method for LLM-based ASR uses new entropy allocation metrics to achieve competitive benchmark performance with 2.3B parameters while mitigating hallucinations via better encoder-LLM decoupling.
-
MedASR: An Open-Source Model for High-Accuracy Medical Dictation
MedASR is an open-source 105M-parameter ASR model achieving 58% relative WER reduction versus Whisper Large-v3 on medical dictation.
-
NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR
NIM4-ASR delivers SOTA ASR performance on public benchmarks using a 2.3B-parameter LLM with multi-stage training, real-time streaming, and million-scale hotword customization via RAG.