HEAR: Holistic Evaluation of Audio Representations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911007790596096 |
|---|---|
| author | Turian, Joseph Shier, Jordie Khan, Humair Raj Raj, Bhiksha Schuller, Björn W. Steinmetz, Christian J. Malloy, Colin Tzanetakis, George Velarde, Gissel McNally, Kirk Henry, Max Pinto, Nicolas Noufi, Camille Clough, Christian Herremans, Dorien Fonseca, Eduardo Engel, Jesse Salamon, Justin Esling, Philippe Manocha, Pranay Watanabe, Shinji Jin, Zeyu Bisk, Yonatan |
| author_facet | Turian, Joseph Shier, Jordie Khan, Humair Raj Raj, Bhiksha Schuller, Björn W. Steinmetz, Christian J. Malloy, Colin Tzanetakis, George Velarde, Gissel McNally, Kirk Henry, Max Pinto, Nicolas Noufi, Camille Clough, Christian Herremans, Dorien Fonseca, Eduardo Engel, Jesse Salamon, Justin Esling, Philippe Manocha, Pranay Watanabe, Shinji Jin, Zeyu Bisk, Yonatan |
| contents | What audio embedding approach generalizes best to a wide range of downstream tasks across a variety of everyday domains without fine-tuning? The aim of the HEAR benchmark is to develop a general-purpose audio representation that provides a strong basis for learning in a wide variety of tasks and scenarios. HEAR evaluates audio representations using a benchmark suite across a variety of domains, including speech, environmental sound, and music. HEAR was launched as a NeurIPS 2021 shared challenge. In the spirit of shared exchange, each participant submitted an audio embedding model following a common API that is general-purpose, open-source, and freely available to use. Twenty-nine models by thirteen external teams were evaluated on nineteen diverse downstream tasks derived from sixteen datasets. Open evaluation code, submitted models and datasets are key contributions, enabling comprehensive and reproducible evaluation, as well as previously impossible longitudinal studies. It still remains an open question whether one single general-purpose audio representation can perform as holistically as the human ear. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2203_03022 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | HEAR: Holistic Evaluation of Audio Representations Turian, Joseph Shier, Jordie Khan, Humair Raj Raj, Bhiksha Schuller, Björn W. Steinmetz, Christian J. Malloy, Colin Tzanetakis, George Velarde, Gissel McNally, Kirk Henry, Max Pinto, Nicolas Noufi, Camille Clough, Christian Herremans, Dorien Fonseca, Eduardo Engel, Jesse Salamon, Justin Esling, Philippe Manocha, Pranay Watanabe, Shinji Jin, Zeyu Bisk, Yonatan Sound Artificial Intelligence Machine Learning Audio and Speech Processing What audio embedding approach generalizes best to a wide range of downstream tasks across a variety of everyday domains without fine-tuning? The aim of the HEAR benchmark is to develop a general-purpose audio representation that provides a strong basis for learning in a wide variety of tasks and scenarios. HEAR evaluates audio representations using a benchmark suite across a variety of domains, including speech, environmental sound, and music. HEAR was launched as a NeurIPS 2021 shared challenge. In the spirit of shared exchange, each participant submitted an audio embedding model following a common API that is general-purpose, open-source, and freely available to use. Twenty-nine models by thirteen external teams were evaluated on nineteen diverse downstream tasks derived from sixteen datasets. Open evaluation code, submitted models and datasets are key contributions, enabling comprehensive and reproducible evaluation, as well as previously impossible longitudinal studies. It still remains an open question whether one single general-purpose audio representation can perform as holistically as the human ear. |
| title | HEAR: Holistic Evaluation of Audio Representations |
| topic | Sound Artificial Intelligence Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2203.03022 |