Using child directed speech to bootstrap a model based speech segmentation and recognition system

Brandl H, Joublin F (2008) .

Patent | Published | English

No fulltext has been uploaded

Inventor
;
Abstract
he present invention relates to a technique which exploits the properties of child directed speech to learn the acoustical structure of speech using distinct models for each unit of speech. The resulting acoustic model may e.g. be used for speech segmentation, syllable detection or speech recognition in multi-modal systems. Inherent to the invention proposed here is a system which is able to recognize and learn the structure of speech, which can find application in automatic speech recognition systems and synthetic speech synthesizing systems.
Publishing Year
Int. Patent Number
DE 60 2006 010 395.6
Int. Patent Classification
G10L 15/14
PUB-ID

Cite this

Brandl H, Joublin F. Using child directed speech to bootstrap a model based speech segmentation and recognition system. 2008.
Brandl, H., & Joublin, F. (2008). Using child directed speech to bootstrap a model based speech segmentation and recognition system.
Brandl, H., and Joublin, F. (2008). Using child directed speech to bootstrap a model based speech segmentation and recognition system.
Brandl, H., & Joublin, F., 2008. Using child directed speech to bootstrap a model based speech segmentation and recognition system.
H. Brandl and F. Joublin, “Using child directed speech to bootstrap a model based speech segmentation and recognition system”, 2008.
Brandl, H., Joublin, F.: Using child directed speech to bootstrap a model based speech segmentation and recognition system. (2008).
Brandl, Holger, and Joublin, Frank. “Using child directed speech to bootstrap a model based speech segmentation and recognition system”. (2008).
This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar