Work

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

Year: 2010
Type: conference-paper
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.
Source: HAL
Language: English
Open Access status: green
OpenAlex ID: W2168140849
FWCI: 0.499
Cites: 20
Cited by: 4
Related to: 10