Pepper the Robot to Get Emotional System

The system for human interaction is developed by Affectiva and called Emotion AI
30 August 2018   379

SoftBank Robotics, which created the humanoid robot Pepper, integrates into the system for interaction with the person Emotion AI from Affectiva. It will teach robot to distinguish joy, disgust, surprise, fear and other emotions.

The algorithm uses Pepper cameras and microphones to recognize anger, contempt, disgust, fear, joy, sadness and surprise. The robot will distinguish between a smile and a grin, and also understand when a person is distracted or wants to sleep.

SoftBank Robotics introduced Pepper in 2015. It can understand speech, respond to the interlocutor and maintain conversation through the tablet in the case. It was created as a companion for single people and an assistant for business. For example, in 2015 it worked for a week at the Margiotta Food & Wine store in Edinburgh, but the management dismissed him because the robot could not cope with the tasks. Pepper's answers were too general and did not help customers find the right products, and it also joked inappropriately.

In March 2018, researchers found vulnerabilities in robots from SoftBank Robotics. Thanks to these findings, intruders can force androids to extort money, show pornography in public places and swear with clients. Although malware was developed for NAO, the same code can be used for Pepper.

Microsoft to Use AI to Create Human Voice

Synthetic voice is nearly indistinguishable from recordings of people
27 September 2018   457

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.