Speech Technology Magazine

 

Voicebox Launches Voicebox Auto

Voicebox Auto delivers conversational interfaces to automakers
Posted Dec 12, 2017
Page1 of 1
Bookmark and Share

To accelerate the next generation of conversational automotive interfaces, Voicebox has launched Voicebox Auto, which includes stand-alone or fully-hybrid operation, over-the-air updates, broad language support, dialogue support, context sensitivity, multi-modal speech input and output, and more.

Voicebox Auto natively supports hybrid operation, in which user requests can be serviced by the vehicle’s embedded system and cloud-based conversational AI when connected or by the vehicle alone when connectivity is not available. Because each system is distinct, they react slightly differently to user requests. An arbitrator module, powered by the latest machine-learning technology, selects which response to present to the user. The overall system thus outperforms the accuracy of either system alone, generally offering a 5 percent to 10 percent boost in accuracy.

The Voice Trace function will give Voicebox vastly more real-world training data that it can then use to  train voice recognition systems that are impervious to vehicle noise, accurate across a wide range of speaker accents, and tuned for the particular echo patterns of different cabin sizes.

Other features of Voicebox Auto include the following:

  • AI services for intelligent dialogue management;
  • core speech input/output services for dynamic virtual reality and text-to-speech;
  • an application programming interface and software development kit that enables easy development on automakers’ embedded platforms.

Voicebox Auto is following an ambitious roadmap of improvements, including planned increases in scalability to handle billions of utterances per year. Concurrently, Voicebox will leverage increasingly-powerful vehicle systems to improve latency and the user experience through advanced caching, predictive analytics, and OTA features. Conversational Intelligences, which combine semantic parsers for natural conversations, plan-based reasoning, and data sources and services for carrying out intelligent requests, will be tailored to automotive scenarios.

“Location Intelligence” will be the first conversational intelligence for Voicebox Auto. With Location Intelligence, Voicebox Auto will be able to handle complex queries, such as “get me directions to the pizza place across from the movie theater on Cherry Street,” as well as to intelligently understand that requests such as “take me to the Seahawks game” actually mean “find somewhere I can park within easy walking distance of the stadium, and get me directions to that.”


Page1 of 1