@CoditEU Project to train a real time anomaly detection model. MelSpectrogram extraction from .wav -> Data augmentation (rolling, stretching, etc...) -> Generating multi class label (specific failure) with PCA+KMeans -> CNN training on multiclass labeled MelSpectrograms -> Configuring HTTP endpoint with Flask & deploying with Docker -> Uploadin…

Fall 2021 Introduction to Deep Learning - Homework 1 Part 2 (Frame Level Classification of Speech)

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.