Skip to Main content Skip to Navigation
Conference papers

Sparse Coding of Pitch Contours with Deep Auto-Encoders

Nicolas Obin 1 Julie Beliao 2
1 Analyse et synthèse sonores [Paris]
STMS - Sciences et Technologies de la Musique et du Son
Abstract : This paper presents a sparse coding algorithm based on deep auto-encoders for the stylization and the clustering of pitch contours. The main objective of the proposed algorithm is to learn a set of pitch templates that can be easily interpreted by humans and whose combination can approximate efficiently the observed pitch contours. The proposed learning architecture is based on deep auto-encoders, commonly used to learn non-linear and low-dimensional latent representations that approximate the observed data. The proposed deep architecture is based on stacked auto-encoders and the sparsity of the network is investigated in order to learn a more robust and general representation of the pitch contours (dropout, denoising auto-encoder, sparsity regularization). The deep auto-encoding of the pitch contours is illustrated and discussed on the TIMIT American-English speech database † with comparison of other existing stylization and clustering algorithms.
Complete list of metadata

Cited literature [31 references]  Display  Hide  Download
Contributor : Nicolas Obin <>
Submitted on : Friday, March 2, 2018 - 6:45:08 PM
Last modification on : Tuesday, July 13, 2021 - 2:17:13 PM
Long-term archiving on: : Thursday, May 31, 2018 - 8:22:25 PM


Files produced by the author(s)


  • HAL Id : hal-01722007, version 1


Nicolas Obin, Julie Beliao. Sparse Coding of Pitch Contours with Deep Auto-Encoders. Speech Prosody, Mar 2018, Poznan, Poland. ⟨hal-01722007⟩



Record views


Files downloads