Benchmarking Audio-Based Empathetic Response Judgment in Large Audio Language Models
This public demo is hosted in the NLP2CT Lab, University of Macau organization.
index.html contains the static demo website. Sample/ contains the included audio examples from Anno-MI, MESC, and AvaMERG. The full benchmark, prompts, and evaluation scripts are not included in this demo repository.
Download or clone this repository and open index.html in a browser. Keep the Sample/ directory alongside it so the audio players can find their files. No build step is required.
The site is served by GitHub Pages from the root of the main branch at https://nlp2ct.github.io/BaeEmpEval/.
The website code (HTML, CSS, and JavaScript) is available under the MIT License. The BAEmpEval annotations created by the authors are released under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
These licenses do not cover source audio, source transcripts, or other third-party materials. Such materials remain subject to the licenses and access conditions of their original datasets and must be obtained directly from the original providers. This repository grants no additional rights to them.