Investigating the Use of Semi-Supervised Convolutional Neural Network Models for Speech/Music Classification and Segmentation

David Doukhan (1) , Jean Carrive (1)

1 INA - Institut National de l'Audiovisuel

A convolutional neural network architecture, trained with a semi-supervised strategy, is proposed for speech/music classification (SMC) and segmentation (SMS). It is compared to baseline machine learning algorithms on three SMC corpora and demonstrates superior performances, associated to perfect media-level speech recall scores. Evaluation corpora include speech-over-music segments with durations varying between 3 and 30 seconds. Early SMS results are presented. Segmentation errors are associated to musical genres not covered in the training database, and/or with close to speech acoustic properties. These experiments are aimed to help the design of novel speech/music annotated resources and evaluation protocols, suited to TV and radio stream indexation.

Mots clés: Speech/music discrimination; Audio segmentation; Convolutional Neural Networks; Music Information Retrieval; Multimedia Indexation

Domaines: Apprentissage [cs.LG]; Réseau de neurones [cs.NE]; Son [cs.SD]

David Doukhan, Jean Carrive. Investigating the Use of Semi-Supervised Convolutional Neural Network Models for Speech/Music Classification and Segmentation. The Ninth International Conferences on Advances in Multimedia (MMEDIA 2017) : , IARIA, Apr 2017, Venise, Italy. ⟨hal-01514228⟩