A bag-of-features framework for incremental learning of speech invariants in unsegmented audio streams

Olivier Mangin 1, * Pierre-Yves Oudeyer 1 David Filliat 1, 2
* Corresponding author
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : We introduce a computational framework that allows a machine to bootstrap flexible autonomous learning of speech recognition skills. Technically, this framework shall en- able a robot to incrementally learn to recog- nize speech invariants from unsegmented au- dio streams and with no prior knowledge of phonetics. To achieve this, we import the bag-of-words/bag-of-features approach from recent research in computer vision, and adapt it to incremental developmental speech pro- cessing. We evaluate an implementation of this framework on a complex speech database.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.inria.fr/inria-00541802
Contributor : Pierre Rouanet <>
Submitted on : Wednesday, December 1, 2010 - 11:41:07 AM
Last modification on : Wednesday, November 29, 2017 - 3:51:15 PM
Document(s) archivé(s) le : Wednesday, March 2, 2011 - 3:00:30 AM

File

mangin.2010.eprirob.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00541802, version 1

Collections

Citation

Olivier Mangin, Pierre-Yves Oudeyer, David Filliat. A bag-of-features framework for incremental learning of speech invariants in unsegmented audio streams. Tenth International Conference on Epigenetic Robotics, 2010, Örenäs Slott, Sweden. ⟨inria-00541802⟩

Share

Metrics

Record views

366

Files downloads

129