# LSTM-RNN-VAD

**Repository Path**: sanghy6/LSTM-RNN-VAD

## Basic Information

- **Project Name**: LSTM-RNN-VAD
- **Description**: Voice Activity Detection LSTM-RNN learning model
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-08-31
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# LSTM-RNN Voice Activity Detection


##### REQUIRED PACKAGES <br />
numpy, tensorflow, libROSA, matplotlib <br />


##### FILES<br />

\- dataset_utils.py <br />
	Dataset related utilities: One-hot encoding, wav file normalisation, TRS to CSV conversion, JSON to CSV conversion, Youtube wav download for the AudioSet Google corpus, Liblinear library data transformations

\- metrics_utils.py <br />
	(NOT FINALISED) Metrics' related utilities for the baseline VAD methods 

\- feature_extractor.py <br />
	Feature extraction class to extract MFCC, deltas, double deltas, RSE

\- VAD_model.py <br />
	LSTM-RNN tensorflow learning model

\- \__main__.py <br />
	The program's main entry point

\- /checkpoint <br />
	Tensorflow checkpoint directory for saving and restoring learning models

\- /parameter <br />
	LSTM-RNN learning model hyper-parameters, training parameters, and log/checkpoint directories names

\- /notebook <br />
	Jupyter notebooks to test initial VAD prototypes