kunzhou9646 / emovox Goto Github PK

Thank you for sharing your code.
In "train_ser.py", line 199, '../transformer_ser/data_500_final.pkl' is loaded, but this file is not found. How do I make this file?

Hi, Mr Zhou,
I have read the paper, the idea of emotion density control is very attractive.
I am not Enligsh native, but I feel the samples of proposed in https://kunzhou9646.github.io/Emovox_demo/ are not so good, they are even less intelligable or natural compared with conterpart samples.
Is the hurt on speech quality a necessary cost when learning to be more emotional?

Hey! Thank you for sharing your work. I was wondering whether you could provide pretrained weights of the final model to check the quality of the conversion on our own samples?

I can not find the relevant python script, could you please help me? Thanks!

Hi Kun, I have read this paper and tried to train this network, but I meet some questions as follows:

1. I cant find the implementation of TextMelIDLoader and TextMelIDCollate, and I want to know whether the strength_embedding is the result of Learned Ranking Function, a value in [0, 1] which indicates the emotional intensity?
2. In Formula (6), why not set a lower bound but an upper bound?
   
3. About DDUR，how can we calculate the DDUR between two sentences of different liguistic content? duration / num_of_words？

Look forward your kind reply! Thank you：）

data_500_final.pkl 您好可以提供一下这个文件吗~感谢感谢！

Hello, Kun! Thanks a lot for the codes you provide. However, I have met some problems when I run the codes. When I used pre-processing.py to extract open-smile features, I couldn't find the files named IS09_emotion.conf and SMILExtract. I want to ask how to get these two files. Hope that you could help me, thanks!

Hi thanks for the code! I was struggling with the relative attributes training part. As is mentioned in #4 (comment), the path is set in the code and it seems nowhere I can find it in this repo.

I'm stuck at here mainly because I want to train your model on a different speaker. I would be better if you can share the csv files strengths.txt related to the Mixed Emotion repo on another speaker (especially 0015). Thank you!

Hello, Thank you for sharing your work!

I have a question in the "step1. Learning relative attributes" part, pre-processing.py.
In the process of extracting the acoustic features with openSMILE feature, which file is used in the following path?

opensmile_path = '/Users/kun/Desktop/workspace/open_smile/opensmile/build/progsrc/smilextract/SMILExtract'
config_path = '/Users/kun/Desktop/workspace/open_smile/opensmile/config/is09-13/IS09_emotion.conf'

I couldn't find a specific way to specify the path in the paper.

请问怎么样才可以下到opensmile提取音频特征的文件呢？