On Dec. 25, Apple received a patent for a method that would greater enhance naturalness in its speech synthesizer. The patent, which was originally filed in 2003, assigns prominence to certain words within a sentence, and uses context and word placement as a means of determining emphasis and a more conversational tone. According to the patent’s text, Apple hopes to step up to the plate at a time when, "Most existing TTS systems use simple rules to carry out word prominence assignment."

The listed inventors of the patent, Jerome R. Bellegrada and Kim E.A. Silverman, noted in the filing that Apple’s new speech synthesis model took a holistic view in machine-produced utterances—text is viewed as a whole, and the method works by taking the entire document’s data into account. Relating this information to proper intonation means assigning emphasis to words like "the," that the patent claims "are not ordinarily emphasized." 

Though the patent uses the example of how speech synthesis can benefit a desktop user, Apple’s patent could also benefit mobile applications. Still riding out the iPhone’s wave of success, developers stand poised with the opportunity to install the method for synthesis into Apple's mobile devices.

Jim Larson, an independent consultant at Larson Tech, remains cautiously optimistic about the patent's possible implications. "Apple stands poised to use speech synthesis to its advantage in mobile devices. "Users already use the iPhone as a phone, so it is a small step for users to listen to text information via speech synthesis," he says. "However, to be really useful, the iPhone also needs speech recongition so the user can request to listen to a specific tune, email, and voice message, etc."