The future approaches! Advances in speech recognition and generative dialog models has led to the rise in the popularity of conversational interfaces like chatbots and virtual agents.
However, these conversations are still not natural, and end up being only transactional in nature.
Microsoft wants to change this.
And in order to do so, the company has filed for a won a patent for a technology that brings what the company calls an end-to-end voice based conversational agent that has the ability to engage in a more natural, multiturn dialog.
In other words, the discourse will align with the conversational style and facial expressions of a user.
The patent explains this in more detail:
“A conversational agent that is implemented as a voice-only agent or embodied with a face may match the speech and facial expressions of a user. Linguistic style-matching by the conversational agent may be implemented by identifying prosodic characteristics of the user’s speech and synthesizing speech for the virtual agent with the same or similar characteristics.
The facial expressions of the user can be identified and mimicked by the face of an embodied conversational agent. Utterances by the virtual agent may be based on a combination of predetermined scripted responses and open-ended responses generated by machine learning techniques. A conversational agent that aligns with the conversational style and facial expressions of the user may be perceived as more trustworthy, easier to understand, and create a more natural human-machine interaction.”
Human-machine interactions redefined.
The United States Patent and Trademark Office (USPTO) granted Microsoft this patent on September 3, 2020. And it goes by the very convenient name of Linguistic Style Matching Agent.
Interestingly, the conversation agent can either be audio only, or embodied. That is to say, it has a face that appears to speak. In both these implementations, the agent uses machine learning techniques to respond to what the user says in order to respond in a more natural and understandable way.
Way of the future this.
