At its flagship "re:Mars" event here, the company showed a brief demo and announced that in the coming months, this and other multi-skill experiences will roll out to Alexa customers, initially in the US.
"We envision a world where customers will converse more naturally with Alexa: seamlessly transitioning between skills, asking questions, making choices, and speaking the same way they would with a friend, family member or co-worker," Rohit Prasad, Alexa Vice President and Head Scientist, told a packed house.
"Our objective is to shift the cognitive burden from the customer to Alexa," Prasad added.
Today, customer exchanges with Alexa are generally either one-shot requests, like "Alexa, what's the weather?", or interactions that require multiple requests to complete more complex tasks.
An Alexa customer planning a family movie night out must interact independently with multiple skills to find a list of local theatres playing a particular movie, identify a restaurant near one of them, and then purchase movie tickets, book a table, and perhaps order a ride.
The cognitive burden of carrying information across skills such as time, number of people, and location rests with the customer.
Enabling a new experience is a set of AI modules that work together to generate responses to customers' questions and requests.
The new approach to multi-turn dialogue also includes a separate AI module whose task is to decide when to switch between different skills which questions to pass to the restaurant search skill, for instance, and which to pass to the movie skill," informed Prasad.
"With this new approach, Alexa will predict a customer's latent goal from the direction of the dialogue and proactively enable the conversation flow across topics and skills. This is a big leap for conversational AI," informed Prasad.
He also announced the developer preview of "Alexa Conversations", a new deep learning-based approach for skill developers to create more-natural voice experiences with less effort, fewer lines of code and less training data than before.
The preview allows skill developers to create natural, flexible dialogues within a single skill; upcoming releases will allow developers to incorporate multiple skills into a single conversation.
"It's way easier to build a complex voice experience with Alexa Conversations due to its underlying deep-learning-based dialog modeling," Prasad noted.
(Nishant Arora can be contacted at nishant.a@.in)
( With inputs from IANS )