Data

Tools

Indexes

Applications

Experiments

Open Source Science

low-complexity-acoustic-scene

Neural Network for Low Complexity Acoustic Scene Classification

https://github.com/ebuka-olisa/low-complexity-acoustic-scene

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.4%) to scientific vocabulary

Keywords

depthwise-separable-convolutions dilated-convolution machine-learning neural-network python
Last synced: 7 months ago · JSON representation ·

Repository

Neural Network for Low Complexity Acoustic Scene Classification

Basic Info
  • Host: GitHub
  • Owner: ebuka-olisa
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 232 KB
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
depthwise-separable-convolutions dilated-convolution machine-learning neural-network python
Created over 3 years ago · Last pushed over 3 years ago
Metadata Files
Readme Citation

README.md

Low Complexity Acoustic Scene Classification

Author: Chukwuebuka Olisaemeka, Anglia Ruskin University Email. Lakshmi Babu Saheer, Anglia Ruskin University Email.

Getting started

  1. Clone repository from Github.
  2. Install requirements with command: pip install -r requirements.txt.
  3. Extract features from the audio files previously downloaded python prepare_data.py.
  4. Create a .h5 file with the extracted features.
    • python create_h5.py --dataset_file='/TAUUrbanAcousticScenes_2022_Mobile_DevelopmentSet/meta.csv' --workspace='path'.
  5. Run the task specific application with default settings for model quantization python task1.py or ./task1.py

Introduction

This is the codebase for our entry in the Low-Complexity Acoustic Scene Classification in Detection and Classification of Acoustic Scenes and Events 2022 (DCASE2022) challenge. You are permitted to build your own systems by extending this system.

Data preparation

|
├── task1_features.yaml   # Parameters for the prepare_data.py file
├── prepare_data.py       # Code to extract features from 1 second files
└── create_h5.py          # Code to create the features_all.h5 file

Network Architecture

Alt Image text

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: >-
  Neural Network for Low Complexity Acoustic Scene
  Classification
message: Please cite this software using these metadata.
type: software
authors:
  - given-names: Chukwuebuka
    family-names: Olisaemeka
    email: olisaemekaebuka@gmail.com
    affiliation: Anglia Ruskin University
  - given-names: Lakshi
    family-names: Babu Saheer
    email: lakshmi.babu-saheer@aru.ac.uk
    affiliation: Anglia Ruskin University
repository-code: >-
  https://github.com/ebuka-olisa/low-complexity-acoustic-scene
commit: bac0323cd7c8bb9621ea56af9843386342bcfa3f
date-released: '2022-07-12'

GitHub Events

Total
Last Year

Dependencies

requirements.txt pypi
  • absl-py ==0.9.0
  • dcase_util *
  • ipython *
  • librosa *
  • numpy *
  • pandas *
  • pyparsing ==2.2.0
  • pyyaml ==5.4
  • sed_eval >=0.2.0