Tutorial
Video List
Doing some research into Neural Networks, I decided to attempting creating my own following a tutorial and using Python. However, this is just getting used to playing with the coding and equations and getting it to return decent outputs. The tutorial I followed basically tried to just tell if an input was closer to A or B, and use numerical inputs, not audio input.
This code I found can be used to train a network to fill in gaps in audio data. This isn't exactly what I need, but maybe it can be edited to suit my needs.
This presentation marks how automatic speech recognition into text works across various models.
I'm still trying to find codes I can use to recognize audio. Most NNs I've been looking around seem to use TensorFlow and Python, so I will have to look into those more.
Ultimately, I'd like to create or find a neural network to work with that I can input audio data to be recognized. Finding one takes priority considering the amount of inputs needed to affect a face model. I'd like to look into more complex neural networks in the upcoming weeks and code I can play around with without building from scratch.
Update: Maybe this code can help with audio recognition?
Video List
Doing some research into Neural Networks, I decided to attempting creating my own following a tutorial and using Python. However, this is just getting used to playing with the coding and equations and getting it to return decent outputs. The tutorial I followed basically tried to just tell if an input was closer to A or B, and use numerical inputs, not audio input.
This code I found can be used to train a network to fill in gaps in audio data. This isn't exactly what I need, but maybe it can be edited to suit my needs.
This presentation marks how automatic speech recognition into text works across various models.
I'm still trying to find codes I can use to recognize audio. Most NNs I've been looking around seem to use TensorFlow and Python, so I will have to look into those more.
Ultimately, I'd like to create or find a neural network to work with that I can input audio data to be recognized. Finding one takes priority considering the amount of inputs needed to affect a face model. I'd like to look into more complex neural networks in the upcoming weeks and code I can play around with without building from scratch.
Update: Maybe this code can help with audio recognition?
Comments
Post a Comment