Speech-Emotion-Recognition icon indicating copy to clipboard operation
Speech-Emotion-Recognition copied to clipboard

Speech emotion recognition implemented in Keras (LSTM, CNN, SVM, MLP) | 语音情感识别

Results 30 Speech-Emotion-Recognition issues
Sort by recently updated
recently updated
newest added

兩分鐘的音頻或是一句話幾秒鐘的音頻,哪個合適?還是都可以?

Bumps [tensorflow](https://github.com/tensorflow/tensorflow) from 2.8.0 to 2.11.1. Release notes Sourced from tensorflow's releases. TensorFlow 2.11.1 Release 2.11.1 Note: TensorFlow 2.10 was the last TensorFlow release that supported GPU on native-Windows. Starting...

dependencies

作者您好,非常荣幸可以在GitHub上面看到您的语音情感识别的项目,我在运行起来您的项目之后,对于CASIA给出的样本音频进行预测,都是准确的,但是使用我在视频中截取的音频进行预测,识别结果不太理想,我想问一下您,就是这个是音频的问题,还是您的项目需要我自己先训练出来一个模型再做预测,然后麻烦问一下您,就是你项目给出的模型准确率大概是多少呀,您说的准确率到80%是怎么实现的呀,可以告诉我一下嘛,如果可以的话,您可以提供一份效果比较好的预训练好的模型供我学习嘛。如有打扰,十分抱歉。非常感谢您的项目对我的帮助,祝您生活愉快!

Hi, Is it possible to get the CASIA dataset? Is this one closed-door dataset? Is there any way to buy it? Best, Lance

使用其他测试音频,修改了路径,但是预测出来的还是原来作者给的预测结果,音频波形图更新了,请问作者是哪一步固定了吗

Bumps [joblib](https://github.com/joblib/joblib) from 1.1.0 to 1.2.0. Changelog Sourced from joblib's changelog. Release 1.2.0 Fix a security issue where eval(pre_dispatch) could potentially run arbitrary code. Now only basic numerics are supported....

dependencies

想问下,librosa和opensmile的配置相比,哪个效果更好?

在运行`python preprocess.py --config configs/cnn1d.yaml`时,出现`sh: ./SMILExtract: No such file or directory` 求解决 ![image](https://github.com/Renovamen/Speech-Emotion-Recognition/assets/88299695/38a105f1-0c4a-4acb-af46-e0b8916e2c6a)

请问各位大哥大姐们,在训练LSTM模型的时候,有没有碰到这种过拟合问题啊?应该如何解决呢? ![output_acc1](https://github.com/Renovamen/Speech-Emotion-Recognition/assets/67530353/abb68826-6fa9-4e27-83f2-25aeec9e1129) ![output_loss1](https://github.com/Renovamen/Speech-Emotion-Recognition/assets/67530353/02da149b-2222-4ec5-8ad5-99f7f6fbad9b)