philipperemy / deep-speaker

Deep Speaker: an End-to-End Neural Speaker Embedding System.
MIT License
905 stars 241 forks source link

Can I use it for sentimental analysis. #103

Open kishan2k2 opened 12 months ago

kishan2k2 commented 12 months ago

So I want to do a sentimental analysis of the audio using your model.

Can some one answer me if it is possible? if yes then how can I do it?

kishan2k2 commented 12 months ago

Please let me know if I am wrong.

I will first collect a dataset to fine-tune the model. secondly, I will get the embedding of each of the voice audio corresponding to a label. Now I will train any machine learning or deep learning model for that to recognize the label when an audio embedding is given.

Now for any new audio I want to test I will extract its embedding and then predict the label with the trained model.

Seems pretty convincing to me.