2008 | OriginalPaper | Buchkapitel
Introduction
verfasst von : Eberhard Hänsler, Gerhard Schmidt
Erschienen in: Speech and Audio Processing in Adverse Environments
Verlag: Springer Berlin Heidelberg
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
If people would speak digitally speech processing would lack some of its most challenging problems.
Systems for speech enhancement have to perform at least three main functions: echo canceling, noise suppression and speech restoration. For all three there is no clear-cut solution. Mathematical approaches have to start with models that are simplified to a high degree and such are a very rough approximation to the reality only. Necessarily, a good deal of heuristics has to enter the solution in order to match it to the real world. Thus, there are no break throughs to final solutions in any one of the subproblems. Advanced technology and cheaper hardware will always stimulate researchers and industrial developers to come up with more sophisticated methods that promise better results. The appearance of powerful simulation tools and high-capacity personal computers over the last decades have speeded up this process. The simulation and the real-time verification of algorithms do no longer require costly dedicated soft- and hardware.
This book provides an overview of recent developments and new results reported from the key researchers in speech and audio processing.