2014 | OriginalPaper | Buchkapitel
Today’s Challenges for Embedded ASR
verfasst von : Jozef Ivanecký, Stephan Mehlhase
Erschienen in: Mathematical and Engineering Methods in Computer Science
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Automatic Speech Recognition (ASR) is pervading nowadays to areas unimaginable a few years ago. This progress was achieved mainly due to massive changes in the “Smart phones world” and ubiquitous availability of small, and powerful Linux-based hardware.
Recently, the availability of free ASR systems with acceptable speed and accuracy performance grew. Together with the changes the mobile world brought, a developer is now able to include ASR quickly without detailed knowledge of the underlying technology. What will be the future of embedded ASR systems in this case?
This talk presents two embedded ASR applications and points out their advantages over today’s quick solutions. The first one demonstrates how changes in users behavior allowed to design a usable voice enabled house control. The second one is an extremely reliable in–car real–time ASR system which can even use a remote ASR for complex tasks.