Microsoft to Use AI to Create Human Voice

Synthetic voice is nearly indistinguishable from recordings of people
27 September 2018   2202

Researchers from Microsoft recorded computer voice, imitating human speech. To overcome the difficulties of the traditional model, they used neural networks for speech synthesis. Microsoft promises to provide support for 49 languages ​​and the ability to create unique voices for the needs of companies in the near future.

Synthesis of speech with the help of neural networks involves comparing the stress and length (so-called prosody) of the speaker's speech units, as well as their synthesis into a computer voice. In systems of traditional speech synthesis, prosody is divided into acoustic and linguistic analysis, controlled by various models. As a result, the speech is noisy and indistinct. Representatives of Microsoft argue that in the model of neural synthesis two stages are combined into one, so the voice sounds like a real one.

The developers are convinced that the synthesis of speech with the help of neural networks will make it more natural to communicate with virtual interlocutors and assistants. Moreover, it will enable you to convert e-books into audiobooks and will allow you to change the scoring of built-in navigators.

Microsoft Neural TTS
Microsoft Neural TTS

Azure computing power is available for real-time use, and Azure Kubernetes is responsible for this. Simultaneous application of neural synthesis of speech together with traditional speaks about expansion and increase of availability of service. At the moment, there are a female voice named Jessa and a man named Guy.

Microsoft is competing in speech recognition and synthesis technologies with Google, which updated its services in late August 2018. Google Cloud announced the release of a stable API for the synthesis of speech Cloud Text-to-Speech with the experimental function of audio profiles and support for several new languages. 

Google to Release Teachable Machine 2.0

Teachable Machines 2.0 is a platform where neural networks can be trained without programming
11 November 2019   52

Learning machine learning is now easier than ever. Google is ready to help with this: the company introduced the Teachable Machine 2.0 platform. This is a site where neural networks can be trained in a couple of clicks.

A camera and microphone are enough to make datasets with video or audio recordings on which the neuron network will be trained. You do not need to write code at all. The interface is extremely simple: one button for recording data, another for training the model. If the result does not suit you, you can delve into the advanced settings or refine the data. You can export your achievements to the application, to a third-party site, to your device, or to Google Drive.

The project has a first version. It allowed training neural networks based on images and did not support the export of models. Teachable Machine was used to familiarize students with AI, as well as to develop useful functional tools, for example, applications that help people with speech impairments communicate.

Give it a try now!