Apple publishes new machine learning articles detailing Siri’s new synthetic voices

Apple publishes new machine learning articles detailing Siri’s new synthetic voices
August 23 21:49 2017

Apple on Wednesday published three new articles detailing the deep learning techniques used for the creation of Siri’s new synthetic voices, as well as covering other machine learning topics it’ll be sharing later this week at the Interspeech 2017 conference in Stockholm, Sweden.

The following new articles from the Siri team are now available:

If you have trouble grasping the technicalities and even understanding the highly technical language in these articles, you’re not alone. While I have no problem whatsoever diving deep in Apple’s complex documentation for developers and other specialized documentation, I feel stupid just by reading those detailed explainers.

Among other improvements, iOS 11 delivers more intelligence and a new voice for Siri.

No longer does the personal assistant uses phrases and words recorded by voice actors to construct sentences and responses. Instead, Siri on iOS 11 adopts programmatically created male and female voices. This is a much harder voice synthesis technique that allows for some really cool possibilities.

For instance, the new Siri voices take advantage of on-device machine learning and artificial intelligence to adjust intonation, pitch, emphasis and tempo while speaking, in real time and based on context of the conversation. Apple’s article titled “Deep Learning for Siri’s Voice” details deep learning techniques behind iOS 11’s Siri voice improvements.

“Siri is a personal assistant that communicates using speech synthesis,” reads the opening paragraph. “Starting in iOS 10 and continuing with new features in iOS 11, we base Siri voices on deep learning. The resulting voices are more natural, smoother, and allow Siri’s personality to shine through.”

The new write-ups were published on the official Apple Machine Learning Journal blog, which was established a few weeks ago to cover the company’s efforts in the field of machine learning (ML) and artificial intelligence (AI) research.

Apple went ahead with the blog following criticism that it couldn’t hire the brightest minds in AI and ML because the company wouldn’t let them publish their works.

Apple’s inaugural post, titled “Improving the Realism of Synthetic Images”, was published on the aforementioned blog in July. The in-depth article outlines a new method for improving the realism of synthetic images from a simulator using unlabeled real data while preserving the annotation information.

view more articles

About Article Author

write a comment


No Comments Yet!

You can be the one to start a conversation.

Add a Comment

Your data will be safe! Your e-mail address will not be published. Also other data will not be shared with third person.
All fields are required.