TIM-Net_SER
TIM-Net_SER copied to clipboard
Jiaxin-Ye
[ICASSP 2023] Official Tensorflow implementation of "Temporal Modeling Matters: A Novel Temporal Emotional Modeling Approach for Speech Emotion Recognition".
配置环境错误
按照requirements里的要求，创建wsl下的虚拟环境（python=3.9）直接运行命令（$ pip install -r requirement.txt），最后显示错误： ERROR: Ignored the following versions that require a different python version: 0.52.0 Requires-Python >=3.6,=3.6,
Hello, thank you for your feedback on feature extraction! I have few more questions: 1. You mention that you use different signal length for different datasets, how did you estimate...
This pull request adds a Pytorch version of the TIMNET architecture together with extendable training and evaluation pipelines that follow the already existing code relying on TF/Keras. This addition could...
数据处理错误
您好，每条语音在提特征的时候，语音在EMOVO中的f1、f2等等文件夹，并不在EMOVO中happy、sad等文件夹，您是怎么做的呢？把所有语音都复制进每个情绪文件夹下？
Hello, I want to test the pretrained models on the audio files, however i was able to test it from the EMODB.npy file that is provided there, but I was...
nice work! If you could provide a download link for the original dataset or supply the raw data (assuming there are no copyright issues), that would be absolutely perfect.
作者你好，根据这个TensorFlow的版本，我用pytorch重写了一遍，但是EMOCAP上精度差3个点，方便看下有啥问题吗？ https://github.com/zhouying3/TIM_net_pytorch
Hi, thank you for your great contribution, this project is really great, but I have a few questions about the use process. I want to train a weight using my...
