HEAR NeurIPS 2021 Submitted Models (Holistic Evaluation of Audio Representations)

This is a mirror of audio representation models that are HEAR API compatible, submitted to the HEAR 2021 NeurIPS challenge: Holistic Evaluation of Audio Representations.

To use these models, please see the hear2021-submitted-models repository. For more information about HEAR, see the HEAR 2021 website, upcoming PMLR journal article, and the HEAR 2021 datasets on Zenodo.

The aim of this challenge is to develop a general-purpose audio representation that provides a strong basis for learning in a wide variety of tasks and scenarios. The HEAR 2021 challenge invites you to create an audio embedding that is as holistic as the human ear, i.e., one that performs well across a variety of everyday domains: What approach best generalizes to a wide range of downstream audio tasks without fine-tuning? HEAR 2021 evaluates audio representations using a benchmark suite across a variety of domains, including speech, environmental sound, and music.