Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers.

Yuan Gong 0001 Sameer Khurana Leonid Karlinsky James R. Glass Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers. 2023 abs/2307.03183 CoRR https://doi.org/10.48550/arXiv.2307.03183 db/journals/corr/corr2307.html#abs-2307-03183