Classifying Spoken Location Names
summary
A concrete demo of a spoken-location classifier using pyAudioProcessing extracts MFCC and GFCC plus spectral features and trains an SVM with scikit‑learn and visualizes with Matplotlib. Training on female-only voices (23 London, 23 Boston) and testing on male voices (17 each) yields MFCC 8/17 London 9/17 Boston, GFCC 13/17 each, and GFCC+spectral 15/17 London 14/17 Boston. Mixing genders in training (23 each) improves MFCC to 9/17 London 14/17 Boston and GFCC+spectral to 15/17 and 14/17.
AI-written summary · about
chapters (3)
related talks
31mClassifying Audio into Types using Python
40mBuilding Features and Machine Learning Models for Audio Signals
40mGathering Insights from Audio Data
22mImplementation and analysis of deep learning models for speech classification
29mRecognizing Speech in Python
28mHow to use Deep Learning to process audio data and classify sounds.
25mLooking at Sound
23mTowards Author Profiling - A Methodology for Gender Expression Classification