(Photo: freestocks on Unsplash)
An iMessage can be turned into a voice note and then played back using a custom voice generated by the recipient’s phone using samples of the original sender’s voice. This is the technology described in a recent Apple patent filing, as reported by Apple Insider.
New patent
Apple customers can already send audio recordings via iMessage or have text messages read aloud by Siri. Still, this new patent offers a technique to have the device read the text message using the sender’s voice instead of Siri using a voice file.
Specifically, the voice model is sent to a second electronic device, as stated in the patent. An example is a message received from a user of a second electronic device.
Qiong Hi, Jiangchuan Li and David A. Winarsky came up with the idea that became the basis for the patent. Li is a senior Siri software engineer for machine learning at Apple, while Hu is a former Apple employee who worked on Siri. Winarsky is the director of text-to-speech technologies.
How will it work?
A user can send an iMessage with an attached voice recording that remains on the device. In that case, the recipient will be given the option of receiving the message or audio recording.
“In response to receiving the message, a speech model of the affected user is received … Based on the speech model, an audio output corresponding to the received message is provided,” the patent reads.
A Siri-like profile of the sender’s voice would then be created, and the recipient’s iPhone would use that profile to mimic the sender’s voice when reading that message and any future messages from that sender. The speech simulation model may be distributed separately so that the recipient’s contacts can download and try it before receiving messages.
Instead of hearing Siri’s voice when it reads messages, it would provide a more personalized experience for friends and family to contact each other. Apple has put a lot of effort into adding that personal touch.
Read also: Apple RCS: iMessage features not yet changed despite EU legislation for universal messaging system
Apple patents
With Apple’s recent efforts in artificial intelligence (AI) and speech recognition, the idea is plausible. For example, in iOS 11, Apple replaced voice acting recordings with a text-to-speech algorithm based on machine learning for Siri.
In 2020, Apple bought the company Voysis, which focused primarily on improving the use of natural language processing by virtual assistants. WaveNet, developed by Google’s DeepMind initiative, was used.
Using so-called “deep generative models of raw audio waveforms,” WaveNets can be trained to create a speech that accurately imitates any human voice.
Apple has also started using AI narration for some audiobook genres instead of human narrators. That Apple gadgets could one day be trained to recognize spoken communication is very likely, according to the patent.
Read also: Apple iOS 16.4 lets Safari Web App send push notifications on iPhones
ⓒ 2023 TECHTIMES.com All rights reserved. Do not reproduce without permission.