Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers
Abstract
In this paper, we focus on Whisper, a recent automatic speech recognition model trained with a massive 680k hour labeled speech corpus recorded in diverse conditions. We first show an interesting finding that while Whisper is very robust against real-world background sounds (e.g., music), its audio representation is actually not noise-invariant, but is instead highly correlated to non-speech sounds, indicating that Whisper recognizes speech conditioned on the noise type. With this finding, we build a unified audio tagging and speech recognition model Whisper-AT by freezing the backbone of Whisper, and training a lightweight audio tagging model on top of it. With <1% extra computational cost, Whisper-AT can recognize audio events, in addition to spoken text, in a single forward pass.
Keywords
Cite
@article{arxiv.2307.03183,
title = {Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers},
author = {Yuan Gong and Sameer Khurana and Leonid Karlinsky and James Glass},
journal= {arXiv preprint arXiv:2307.03183},
year = {2023}
}
Comments
Accepted at Interspeech 2023. Code at https://github.com/yuangongnd/whisper-at