情感检测讲话 [英] Emotion detection in speech

问题描述

我想建立一个应用程序分析的演讲，从话筒的情感内容。

I would like to build an app which analyses the emotional content of speech from the mic.

这不，虽然有时作为一个额外的功能，包括语音识别。情感分析是基于语音的韵律特征（音高变化，速度等信息，音）。

THis does not, although sometimes used as an extra feature, involve speech recognition. Emotional analyses is based on prosodic features of the voice (pitch change, speed etc., tone).

我知道这可以在台式机上完成，但我不希望用户必须上传自己录制（电话交谈）的服务器，以获得情绪的反馈。

I know this can be done on a desktop computer, but i dont want users to have to upload their recordings (phone conversations) to a server in order to get emotional feedback.

我需要的是一个API，它无论是提供整体分析或API，我可以用它来提取这些特征（即对话的平均速度）。

What i need is an API which either provides the whole analyses or an API which i can use to extract those features (i.e. the average speed of the conversation).

有没有这样的东西在那里？

Is there such thing out there?

在此先感谢！

推荐答案

勾选此OpenEAR包，它应该提供一切都在最新的状态艺术水平

Check this OpenEAR package, it should provide everything at the latest state art level

http://sourceforge.net/projects/openart/

在这里阅读有关

HTTP：//www.mmk.ei.tum。德/公共区域/ PDF / 09 / 09eyb1.pdf

慕尼黑openEAR工具包是一套完整的自动语音情感识别。它的缩写代表开放的情感与情感识别工具包。它是基于openSMILE特征提取，从而能够实时在线情绪识别。在各种标准语料库pre训练模式都包括在内，以及脚本和工具来快速构建和评估定制模型集。由于目前包括分类的支持矢量机使用LIBSVM libray。马上要到了，也双向长短期内存回归神经网，木里判别名义贝叶斯网络，和懒惰学习者。

The Munich openEAR toolkit is a complete package for automatic speech emotion recognition. Its acronym stands for open Emotion and Affect Recognition Toolkit. It is based on the openSMILE feature extractor and thus is capable of real-time on-line emotion recognition. Pre-trained models on various standard corpora are included, as well as scripts and tools to quickly build and evaluate custom model sets. As classifier currently included are Support-Vector Machines using the LibSVM libray. Soon to come are also Bidirectional Long-Short-Term-Memory Recurrent Neural Nets, Discriminative Muli-nominal Bayesian Networks, and Lazy Learners.

openEAR是根据GPL许可证授权的免费软件。第一个版本（包括模型组和pre-编译openSMILE）将很快在Sourceforge：openEAR。同时，请参考openSMILE项目，在这里我们提供了特征提取引擎

openEAR is free software licensed under the GPL license. The first release (including model sets and pre-compiled openSMILE) will be available soon on Sourceforge: openEAR. Meanwhile, please refer to the openSMILE project, where we provide the feature extraction engine.

这篇关于情感检测讲话的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！