amanbasu / speech-emotion-recognition

Detecting emotions using MFCC features of human speech using Deep Learning

I am Aman Agarwal 👨‍💻

• R&D Engineer at Synopsys Inc.
• Skilled in deep learning 🤖, android, and cloud.
• If not a programmer 💻, I would be a body builder 💪.
• Certified AWS ML specialist, solutions architect, and developer ☁️✔️.
• Certified TensorFlow developer.

Connect with me

speech-emotion-recognition's Issues

Emotion values

can you provide the script for getting emotion_values.csv file?

Link for Dataset

Hi, Hope you are doing well.

I found your approach very interesting and useful for me as well. The link for Dataset that you have shared doesn't exist, so could you please share the dataset with me so that it would really helpful for implementing.

Thanks in advance, appreciate your help.

FUNCTION OF BUCKET ITERATOR

I want to know what is the main function of bucket iterator and what are parameters and return value.

Where is the speech_emotion_data.pkl?

Hello Aman:

Thank you for enjoying your code.I am trying to follow your code.But I don't find the "speech_emotion_data.pkl" in the file of "speech_emotion_gpu.py".So please could you provide the speech_emotion_data.pkl ? Thanks very much.

Best wishes!

Data Prep

Hello Aman,

Quick question, how did you prepare your IEMOCAP data for loading to the model? I am trying to replicate your code but dont know how to pre-process the data.

No Features columns in create_mfcc.ipynb

In create_mfcc.ipynb, Features column does not exist in the 'file' dataframe. I would appreciate if you could share the code for generating features such as F0 (pitch), voice probability, zero-crossing rate and so on.

Link for speech_emotion_data.pkl

Hi,
Could you please provide me the link for speech_emotion_data.pkl file that you used in speech_emotion_gpu.py python file.
And also if possible could you upload the requirements.txt file to know the versions of the packages you used since I was facing so many errors with version changes.

Thanks in advance!

misssing files Ses01F_script01_2_F008.wav and microsoft_32_features.pkl

Dear sir,

I appropriate your work, i'm student at GMR Institute of Technology,Rajam. As a part of the Project, i am working (Speech to emotion recognition using RNN). For reference i have seen your github. (https://github.com/amanbasu/speech-emotion-recognition.git).

But there are some files are missing in the repository.

Could you please share those data with me?

Ses01F_script01_2_F008.wav
microsoft_32_features.pkl

i couldn't understand the

"path_to_database/IEMOCAP_database/Session{}/wav//.wav".

because of this i couldn't able to load the data...Please help me in this regard

Please respond to the mail as early as possible

Thank you.

zero_crosses should be '/320' not '/0.02', shouldn't it?

In extract_features.py, the following code should be /320 not /0.02, shouldn't it?

zero_crosses = np.nonzero(np.diff(sig[start:end] > 0))[0].shape[0]/0.02 # zero crosses

↓ modify

zero_crosses = np.nonzero(np.diff(sig[start:end] > 0))[0].shape[0]/ 320 # zero crosses

※ Zero Crossing Rate : The rate of sign-changes of the signal during the duration of a particular frame. [1]

ref.[1]: https://github.com/tyiannak/pyAudioAnalysis/wiki/3.-Feature-Extraction