kapre: Keras Audio Preprocessors
Audio processing by using pytorch 1D convolution network
UrbanSound classification using Convolutional Recurrent Networks in PyTorch
Perform three types of feature extraction: STFT, MFCC and MelSpectrogram. Apply CNN/VGG with or without RNN architecture. Able to achieve 95% accuracy.
Learnable STRF, from Riad et al. 2021 JASA
A packaged convolutional voice activity detector for noisy environments.
There are already many projects underway to extensively monitor birds by continuously recording natural soundscapes over long periods. However, as many living and nonliving things make noise, the analysis of these datasets is often done manually by domain experts. These analyses are painstakingly slow, and results are often incomplete.
An example repository to analyze cough audio data using transfer learning
This repository is mainly about the classification of music genres of Kaggle music dataset in various forms of data preparation
Using Deep Convolutional Generative Adversarial Networks to generate new spoken digits.
Fall 2021 Introduction to Deep Learning - Homework 3 Part 2 (RNN-based phoneme recognition)
Add a description, image, and links to the melspectrogram topic page so that developers can more easily learn about it.
To associate your repository with the melspectrogram topic, visit your repo's landing page and select "manage topics."