DGSNA dynamically generates scene-specific noise via prompt-driven language models and text-to-audio diffusion, then mixes it with speech to improve recognition and keyword spotting robustness by up to 11.32%.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DGSNA: Dynamic Generative Scene-based Noise Addition method
DGSNA dynamically generates scene-specific noise via prompt-driven language models and text-to-audio diffusion, then mixes it with speech to improve recognition and keyword spotting robustness by up to 11.32%.