Sample-Rate Agnostic Recurrent Neural Networks

The Problem

Processing 192 kHz signal through an LSTM network trained on 96 kHz data.

The Solution

Signal flow for a neural network with a single recurrent layer.
Signal flow for the same RNN, with sample rate correction. F_target refers to the target sample rate, while F_training refers the the training sample rate.

Case: Integer Multiple Sample Rate

Processing signal through an LSTM network, using a target sample rate of 2 or 3 times the training sample rate, with sample rate correction.

Case: Non-Integer Multiple Sample Rate

Signal flow for the same RNN, with sample rate correction using a fractional delay line with linear interpolation.
Processing signal through an LSTM network, using a target sample rate that is a non-integer multiple of the training sample rate, with sample rate correction.

Limitations

Conclusion

--

--

--

Jatin Chowdhury is a student.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Transferring large CSV files into a relational database using dingDONG

How To Machine Learning — Simple Linear Regression

Privacy-Preserving Training/Inference of Neural Networks, Part 3

Star Bucks Udacity Data Scientist Nanodegree Capstone Challenge

Word Embedding

Building and deploying a machine learning model with automated ML on Azure.

Understanding Image Contrast Algorithms

Ultimate Optimization of GEMM on Maxwell GPU: the dissect of Maxas assembler

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Jatin Chowdhury

Jatin Chowdhury

Jatin Chowdhury is a student.

More from Medium

An Easy Explanation of Kalman Filter

How do NeRFs work?

Measurement of object (grain) sizes in an image using scikit-image from python

How to “Hellow World” in different programming languages