Hello
As a professional AI / Deep learning engineer, I have 8 years of hands on and practical experience in this filed.
This is a Speech/Audio recognision and prediction research, I suggest to use tensorflow and caffe2 deep learning framework.
These deep learning frameworks are especially best for your work and written in C++ which makes it fast.
I have strong experties in Speech recognision, Computer Vision like OpenCV and deep learning tech like CNN, RNN, GAN, DBF, RBM and specific detection models like mobilenet, resnet, densnet, and yolo series.
And Deep learning frameworks like tensorflow, pytorch, keras and caffe2
I have rich experience in C, Python, Java, C# programming languages.
What's more, I have experience in Scientific research for classification, like plant classification, lung disease classification.
I am free now and can start, continuously support your research.
I have experience in implementation of scientific computer vision reseach papers.
As I can consider your opinion at post, I suggest low budget.
I'd like to work with you
Thank you