This challenge aims to evaluate the capabilities of audio encoders, especially in the context of multi-task learning and real-world applications. Participants are invited to submit pre-trained audio encoders that map raw waveforms to continuous embeddings. These encoders will be tested across diverse tasks including speech, environmental sounds, and music, with a focus on real-world usability. The challenge features two tracks: Track A for parameterized evaluation, and Track B for parameter-free evaluation. This challenge provides a platform for evaluating and advancing the state-of-the-art in audio encoder design.
@article{arxiv.2501.15302,
title = {The ICME 2025 Audio Encoder Capability Challenge},
author = {Junbo Zhang and Heinrich Dinkel and Qiong Song and Helen Wang and Yadong Niu and Si Cheng and Xiaofeng Xin and Ke Li and Wenwu Wang and Yujun Wang and Jian Luan},
journal= {arXiv preprint arXiv:2501.15302},
year = {2025}
}