May 14, 2011
Apple has submitted a patent application for a system that allows users to translate Text-to-Speech and vice versa, according to Patently Apple. The request, which was just published by the U.S. Patent and Trademark Office, could make communicating in difficult environments much easier. The patent is Apple’s way of addressing two different types of situations. The first is when a smart phone user is in a loud location, such as a bar or restaurant where making voice calls is nearly impossible because of the surrounding noise. The second is when a user is in a quiet location, such as in a meeting or at church, when making a voice call would be inappropriate. Apple’s solution is to convert speech into text and prerecorded notifications. According to the patent, Apple suggests four different “embodiments,” which include:
One embodiment of the invention is directed to an iPhone which establishes an audio connection with a far-end user via a communication network. The communication device receives text input from a near-end user, and converts the text input into speech signals. The speech signals are transmitted to the far-end user using the established audio connection while muting audio input to its audio receiving component. In one embodiment, the communication device detects the noise level at the near end. When the noise level is above a threshold, the communication device could automatically activate or prompt the near-end user to activate text-to-speech conversion at any point of a communication such as a phone call. Alternatively, the communication device may playback a pre-recorded message to inform the far-end user of the near-end user's inability to speak due to the excessive noise at the near end. In another embodiment, the near-end user can activate text-to-speech conversion whenever necessary regardless of the detected noise level. The near-end user could enter a text message, which is converted into speech signals for transmission via the established audio connection to the far-end user. In yet another embodiment, the communication device could also perform speech-to-text conversion to convert the far-end user's speech into text for display on the communication device. This feature could be used when the far-end communication device cannot, or is not enabled to, send or receive text messages. The speech-to-text conversion and the text-to-speech conversion could be activated at the same time, or could be activated independent of each other. The far-end communication device communicates with the near-end communication device in audio signals, regardless of whether the speech-to-text conversion or the text-to-speech conversion is activated.Apple is said to be working with Nuance to bring advanced speech recognition to iOS devices. This patent request includes some of what could be included in such a system. Note: According to Patently Apple, Apple credits Baptiste Paquier, Aram Lindahl and Phillip Tamchina as the inventors of patent application 20110111805, originally filed in Q4 2009. What do you think? Leave your comments below.