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

[Review] 6. YOLO ver 2

Why Machine Learning tools are so empowering for digital products but so useless for the pandemic…

Logistic Regression With PyTorch — A Beginner Guide

AgriTech Solutions in Open Source

Setting up your Visual Studio Code Tools for AI

Algorithmic Complexity

CNN-LSTM: Predicting Daily Hotel Cancellations

Detecting Spam in Youtube Comments using Python NLTK

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

Predicting Real-Time Neural Network Performance

Training RL agents in stable-baselines3 is easy

Cross-Entropy but not without Entropy and KL-Divergence

Practical Pruning of Neural Networks with Intel Neural Network Distiller