Deep generativemodels cangenerate high-fidelity audio conditioned onvarious types of representations (e.g., mel-spectrograms, Mel-frequency Cepstral Coefficients (MFCC)). Recently, such models have been used to synthesize audio waveforms conditioned on highly compressed representations.

We investigate whether post-hoc model explanations are effective for diagnosing model errors-model debugging. In response to the challenge of explaining a model's prediction, a vast array of explanation methods have been proposed. Despite increasing use, it is unclear if they are effective. To start, we categorizebugs,based on their source, into: data, model, and test-timecontamination bugs.

In this paper, we investigate the problem of transferring knowledge not only across architectures butalsoacrosstasks.

For computational efficiency, we report all results on T5BASE models (12 encoder and decoder layers and 222M parameters).