State-of-the-art speech recognizers are trained on predominantly normal speech and have difficulties handling either exceedingly slow and hyperarticulated or fast and sloppy speech. Explicitly instruc...
c ? 2005 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resal...
Names are common in most text-to-speech applications, such as automatic reading of newspapers, reverse directory services and voice communication aids. The letter-tosound rules included in these appli...
This paper presents a framework called GOOFI (Generic Object-Oriented Fault Injection) for experimental dependability validation of embedded computer systems using fault injection. GOOFI is designed t...