Open hritikksingh opened 2 years ago
I am a GSSoC participant. I have some experience with the above requirements, is the issue assigned yet? My approaches would include trying more NN layers or improving on the data.
I am a GSSoC participant. I have some experience with the above requirements, is the issue assigned yet? My approaches would include trying more NN layers or improving on the data.
Okay I am assigning the issue to you. Here is the data set I have used known as RAVDESS : https://www.kaggle.com/uwrfkaggler/ravdess-emotional-speech-audio
@Yara484 do let me know your time requirement to complete this issue.
@hritikksingh Thank you for assigning. I'm not sure of the time commitment yet. What do you suggest as a deadline?
@hritikksingh Thank you for assigning. I'm not sure of the time commitment yet. What do you suggest as a deadline?
10 days?
@hritikksingh Thank you for assigning. I'm not sure of the time commitment yet. What do you suggest as a deadline?
10 days?
Okay great, I'll start working on it and I'll let you know if I need more time.
@hritikksingh So I managed to set up the virtual environment but I am not sure which part of the code contains the frequency analysis model, is it the speech_emotion.py? Wanted to ask to make sure I understand the issue correctly.
@hritikksingh So I managed to set up the virtual environment but I am not sure which part of the code contains the frequency analysis model, is it the speech_emotion.py? Wanted to ask to make sure I understand the issue correctly.
Correct, that's the file.
@hritikksingh Hi, I tried working on the issue but I ran into several roadblocks and needed to study a few things that will take more time. I guess it's better to give the issue to someone else to give others a chance while I spend more time researching.
@Yara484 let me know how much time you require. This program is intended to help others learn, I am glad you are learning.
@Yara484 if you have any issue with the project implementation, do reach out in the discord channel.
@Yara484 it's too long for this issue, do you have any update??? Or else I have to reassign this issue to someone else.
@hritikksingh Sorry for the late reply. I was reviewing some NN concepts but had exams so had to stop for a while. As I mentioned, it is better to assign someone else to give others a chance.
We need to enhance the voice frequency analysis model. Currently, we are using Neural Network with some basic layers. Requires knowledge of: