Audio Signal Processing

Best thing about data is it can come from anywhere and any source and when it comes to machine learning Audio can play a very important role. We will be using librosa library to practially understand how feature extraction works for audio signals. Audio in Data science can be used…

Wave Digital Filters (WDFs) is a circuit modelling paradigm that has become quite popular in recent years. While using WDFs to emulate circuits made up entirely of series and parallel combinations of elements is fairly straightforward, using WDFs for more complicated circuit topologies is a bit more difficult. The idea…

Based on the ANSI S1.13–2005 standard Your entire body is under pressure. If you’re located in San Francisco today, your body is under approximately 29.9 inHG of atmospheric pressure. This just means the air particles surrounding you are exerting a force against your body by a certain amount. When the…

Sometimes feature extraction with resampling, data augmentation and conversion to Mel spectrograms can seem overwhelming. We found a simpler algorithm to extract Features: MFCC (Mel-frequency Cepstral Coefficients). Paul Mermelstein is typically credited with the development of MFCC. In order to satisfy this technical need, we can implement a logic to…

If you’re using neural networks to process signals in the time domain, you’ve probably run into the following problem: I trained my neural network on data at one sample rate, but now I want to use that network to process data at a different sample rate. The Problem For some types of…

Over the past couple years, I’ve dedicated a significant amount of research time to the implementation of neural networks for real-time audio applications, specifically real-time audio effects that can be used on desktop computers, mobile devices, and embedded devices. …

Introduction Speech recognition is an interdisciplinary subfield of computer science and linguistics that develops methodologies for the recognition of spoken language into text by computers.

Over the last two decades, Wavelet Transform (also known as Wavelet Decomposition) has evolved into a powerful signal processing technique. Let’s start with a brief theoretical overview of the Wavelet Transform. “ The wavelet transform translates the time-amplitude representation of a signal to a time-frequency representation that is encapsulated as…

For the past few years, I’ve been working semi-regularly on an open-source tape emulation audio plugin called CHOWTapeModel. …