An Audio-Based Deep Learning Framework For BBC Television Programme Classification

TL;DR

This paper introduces a deep learning framework that classifies BBC TV programmes by transforming audio into spectrograms, extracting features with CNNs, and achieving high accuracy in genre classification.

Contribution

The paper presents a novel audio-based deep learning approach for TV programme classification using spectrograms and CNNs, demonstrating high accuracy on a BBC dataset.

Findings

Achieved 93.7% average classification accuracy.

Effective use of spectrograms and CNNs for genre classification.

Validated framework on a large BBC dataset.

Abstract

This paper proposes a deep learning framework for classification of BBC television programmes using audio. The audio is firstly transformed into spectrograms, which are fed into a pre-trained convolutional Neural Network (CNN), obtaining predicted probabilities of sound events occurring in the audio recording. Statistics for the predicted probabilities and detected sound events are then calculated to extract discriminative features representing the television programmes. Finally, the embedded features extracted are fed into a classifier for classifying the programmes into different genres. Our experiments are conducted over a dataset of 6,160 programmes belonging to nine genres labelled by the BBC. We achieve an average classification accuracy of 93.7% over 14-fold cross validation. This demonstrates the efficacy of the proposed framework for the task of audio-based classification of television programmes.