latent-toronto-emotion

The **Toronto Emotional Speech Set (TESS)** is a dataset consisting of emotionally charged speech recordings, designed for emotion recognition tasks. This repository provides precomputed **audio embeddings** extracted using the [Music2Latent model](https://github.com/SonyCSLParis/music2latent). These embeddings are derived from the TESS dataset, available at [TESS dataset on Kaggle](https://www.kaggle.com/datasets/ejlok1/toronto-emotional-speech-set-tess), enabling quick and efficient use for tasks like speech emotion recognition. The embeddings can be directly used for classification tasks, without the need for raw audio preprocessing.

**多伦多情感语音数据集（Toronto Emotional Speech Set, TESS）**是一款专为情感识别任务设计、收录带有情感色彩语音录音的数据集。本仓库提供了通过[Music2Latent模型](https://github.com/SonyCSLParis/music2latent)提取的预计算**音频嵌入（audio embeddings）**。这些嵌入源自Kaggle平台可公开获取的TESS数据集（[TESS数据集](https://www.kaggle.com/datasets/ejlok1/toronto-emotional-speech-set-tess)），可被快速高效地应用于语音情感识别等相关任务。该音频嵌入可直接用于分类任务，无需对原始音频进行预处理。