Mel-LLM shows an LLM can achieve competitive ASR by directly ingesting pre-processed Mel spectrogram patches through a linear projection layer.
Robust speech recognition via large-scale weak super- vision,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
On synthetic banking speech alone, GRPO cuts ASR WER 40% relative to SFT (36.71%→22.09%) by improving stopping calibration and attention anchoring to audio.
citing papers explorer
-
LLM can Read Spectrogram: Encoder-free Speech-Language Modeling
Mel-LLM shows an LLM can achieve competitive ASR by directly ingesting pre-processed Mel spectrogram patches through a linear projection layer.
-
When Synthetic Speech Is All You Have: Better Call GRPO
On synthetic banking speech alone, GRPO cuts ASR WER 40% relative to SFT (36.71%→22.09%) by improving stopping calibration and attention anchoring to audio.