MelNet Algorithm to Simulate Person's Voice

It analyzes the spectrograms of the audio tracks of the usual TED Talks, notes the speech characteristics of the speaker and reproduces short replicas
11 June 2019   357

Facebook AI Research team has developed a MelNet algorithm that synthesizes speech with characteristics specific to a particular person. For example, it learned to imitate the voice of Bill Gates.

MelNet analyzes the spectrograms of the audio tracks of the usual TED Talks, notes the speech characteristics of the speaker and reproduces short replicas.

Just the length of the replicas limits capabilities of the algorithm. It reproduces short phrases very close to the original. However, the person's intonation changes when he speaks on different topics, with different moods, different pitches. The algorithm is not yet able to imitate this, therefore long sentences sound artificially.

MIT Technology Review notes that even such an algorithm can greatly affect services like voice bots. There just all communication is reduced to an exchange of short remarks.

A similar approach - analysis of speech spectrograms - was used by scientists from Google AI when working on the Translatotron algorithm. This AI is able to translate phrases from one language to another, preserving the peculiarities of the speaker's speech.

Microsoft to Use Machine Learning For Win 10 Update

Microsoft believes machine learning will reduce the number of errors on different devices during the deployment process
21 June 2019   492

The Windows Update team reported on its Twitter account that it is beginning to train an algorithm that will automatically update all devices on Windows 10, version 1803 and earlier, prior to 1903.

We are now beginning to build and train the machine learning (ML) based rollout process to update devices running the April 2018 Update, and earlier versions of Windows 10, to ensure we can continue to service these devices and provide the latest updates, security updates and improvements. 
 

Windows Update Team

Microsoft considers machine learning will reduce the number of errors on different devices during the deployment of the update. For example, it can prevent driver problems that occur after installing a new version of the OS.