# rajeshraman91/deeplearning-model-for-audio-based-gesture-recognition-in-smartphones architecture

> Architecture diagram of the GitHub repository rajeshraman91/deeplearning-model-for-audio-based-gesture-recognition-in-smartphones, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-08-13). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/rajeshraman91/deeplearning-model-for-audio-based-gesture-recognition-in-smartphones
- Repository: https://github.com/rajeshraman91/deeplearning-model-for-audio-based-gesture-recognition-in-smartphones

## Overview

##### Project type and purpose
- This is a machine-learning training and inference pipeline for audio-based gesture recognition on smartphones.
- It uses two deep-learning model variants (CNN-GRU and LSTM) implemented in Keras/TensorFlow, with Jupyter notebooks and Python scripts for data parsing, preprocessing, model training, and saving the resulting HDF5 model files.

##### File structure
- Top level:
- README.md – project summary
- 2nd_phase/ – contains all code, notebooks, and model artifacts for phase two
- Inside 2nd_phase/:
- Input_Parsing.py – reads and organizes raw audio gesture data
- Input_Preprocessing.py – transforms parsed audio into model-ready features
- main_CNN_GRU.py & main_LSTM.py – training scripts for each model variant
- CNN_GRU_Keras.ipynb & keras_final.ipynb – interactive notebooks for exploratory modeling and final runs
- *.h5 files – serialized trained models (CNN_GRU.h5, LSTM.h5)

##### README
- Very concise: “Audio based Gesture recognition in smart phone by deep learning models – CNN-GRU and LSTM.”

##### Detail and essential architectural elements
- Script/notebook as its own node so reviewers see how responsibilities are divided.

## Diagram (Mermaid)

```mermaid
flowchart TB
    %% Data Source
    RawAudio[(Raw Audio Recording)]:::data

    %% Parsing and Preprocessing
    Parsing["Input_Parsing.py"]:::code
    Preprocessing["Input_Preprocessing.py"]:::code

    %% CNN-GRU Pipeline
    subgraph "CNN-GRU Pipeline"
        direction TB
        CNN_Notebook["CNN_GRU_Keras.ipynb"]:::notebook
        CNN_TrainerScript["main_CNN_GRU.py"]:::code
        CNN_h5[(CNN_GRU.h5)]:::artifact
    end

    %% LSTM Pipeline
    subgraph "LSTM Pipeline"
        direction TB
        LSTM_Notebook["keras_final.ipynb"]:::notebook
        LSTM_TrainerScript["main_LSTM.py"]:::code
        LSTM_h5[(LSTM.h5)]:::artifact
    end

    %% Deployment
    Deployment["Smartphone App / Inference Server"]:::device

    %% Flow connections
    RawAudio -->|"load raw audio"| Parsing
    Parsing -->|"parsed data"| Preprocessing
    Preprocessing -->|"features"| CNN_TrainerScript
    Preprocessing -->|"features"| LSTM_TrainerScript

    CNN_Notebook -->|"interactive tuning"| CNN_TrainerScript
    LSTM_Notebook -->|"interactive tuning"| LSTM_TrainerScript

    CNN_TrainerScript -->|"saved model"| CNN_h5
    LSTM_TrainerScript -->|"saved model"| LSTM_h5

    CNN_h5 -->|"deploy model"| Deployment
    LSTM_h5 -->|"deploy model"| Deployment

    %% Click Events
    click Parsing "https://github.com/rajeshraman91/deeplearning-model-for-audio-based-gesture-recognition-in-smartphones/blob/master/2nd_phase/Input_Parsing.py"
    click Preprocessing "https://github.com/rajeshraman91/deeplearning-model-for-audio-based-gesture-recognition-in-smartphones/blob/master/2nd_phase/Input_Preprocessing.py"
    click CNN_TrainerScript "https://github.com/rajeshraman91/deeplearning-model-for-audio-based-gesture-recognition-in-smartphones/blob/master/2nd_phase/main_CNN_GRU.py"
    click CNN_Notebook "https://github.com/rajeshraman91/deeplearning-model-for-audio-based-gesture-recognition-in-smartphones/blob/master/2nd_phase/CNN_GRU_Keras.ipynb"
    click LSTM_TrainerScript "https://github.com/rajeshraman91/deeplearning-model-for-audio-based-gesture-recognition-in-smartphones/blob/master/2nd_phase/main_LSTM.py"
    click LSTM_Notebook "https://github.com/rajeshraman91/deeplearning-model-for-audio-based-gesture-recognition-in-smartphones/blob/master/2nd_phase/keras_final.ipynb"
    click CNN_h5 "https://github.com/rajeshraman91/deeplearning-model-for-audio-based-gesture-recognition-in-smartphones/blob/master/2nd_phase/CNN_GRU.h5"
    click LSTM_h5 "https://github.com/rajeshraman91/deeplearning-model-for-audio-based-gesture-recognition-in-smartphones/blob/master/2nd_phase/LSTM.h5"
    click README "https://github.com/rajeshraman91/deeplearning-model-for-audio-based-gesture-recognition-in-smartphones/blob/master/README.md"

    %% Styles
    classDef data fill:#b3e6b3,stroke:#333,stroke-width:1px
    classDef code fill:#bdd7ee,stroke:#333,stroke-width:1px
    classDef notebook fill:#fff2cc,stroke:#333,stroke-width:1px
    classDef artifact fill:#c6e0b4,stroke:#333,stroke-width:1px
    classDef device fill:#f4cccc,stroke:#333,stroke-width:1px
```
