Yesterday TechCrunch ran a piece on Supertoy Teddy, a teddy bear toy with true conversational capabilities. Co-creators Ashley Conian and Karsten Fluegge are running a Kickstarter campaign to fund production of the talking bears. These two have experience with conversational technologies. They created Jeannie, a virtual agent / voice assistant app available for the iPhone, Android, and other platforms. In fact, the Jeannie virtual assistant forms the basis of Teddy’s technology.
To get Teddy to work, you need to have the Teddy app (based on Jeannie) installed on your smartphone and your smartphone connected to the Internet. So as not to spoil the magic, you can hide the phone in a zipper pocket in Teddy’s back. That’s where you can also connect the phone to a cable the controls the bear’s robotics.
A microphone picks up voice input when you speak to Teddy and the natural language processing and chatbot capability available with the app kicks in. A speaker acts as Teddy’s voice and the robotics make his mouth open and close when he talks. The Kickstarter campaign links to an early prototype of the talking bear technology.
This is a pretty cool toy! Based on the demos, the bear’s conversational ability seems to be fairly limited at this point, but the possibilities are still intriguing. As with many virtual agents, the rumor is that the Teddy app can learn through conversations. It can supposedly remember things about its conversational partners. The creators are positioning Supertoy Teddy as just that: a toy to engage young children. But they also note on their Kickstarter page that it can serve as a companion for people of all ages.
Could Supertoy Teddy be the start of a trend? Now that virtual agents with voice activated conversational systems are available right from our smartphones, more and more of the objects around us could become true conversational partners. Why watch your TV, for instance, when you can talk to it instead? The future use cases for smart talking systems seems wide open.
Venture Beat recently reported that Google has acquired two speech technology patents from SR Tech Group LLC. A press release from SR Tech Group LLC identified the patents as U.S. Patent No. 7,742,922, titled “Speech interface for search engines” and U.S. Patent No. 8,056,070, titled “System and method for modifying and updating a speech recognition program.”
The filing date for the first patent was November 9, 2006. Reading the abstract of the technology covered by the patent, it sounds like a very generic description of a voice-activated search. The user says what he/she wants to look up, the application uses speech recognition and natural language processing to determine how best to construct the search query, and the application runs the query and returns the result. The second patent describes a system that a user or system administrator can employ to makes updates to the grammar (as in underlying language database) of a speech recognition program.
I’m not a patent attorney, but based on the generic flavor of both of these patents, it seems like Google may have acquired them as a defensive maneuver. Having these broad reaching patents could give them ammunition against other companies that might want to declare future patent infringements in other technology areas. It’s not readily apparent that either patent offers breakthroughs that wold drastically improve Google Now or Google’s recently demonstrated conversational search functionality for Chrome. It’ll certainly be interesting to observe how Google continues to build out speech activated search and how other companies look to compete within the same arena. There seems little doubt that conversational search will play an important role in search, and in virtual agent technologies of the near future.
Chatbots.org reports that CRMXchange is hosting a webinar by virtual agent provider Creative Virtual this Thursday, July 25th. The webinar is geared towards companies and organizations looking for more effective ways to engage their customers across multiple channels (web, social, mobile). Chris Ezekiel, Founder and CEO of Creative Virtual, will showcase how virtual agent technologies are being used by companies such as Verizon, HSBC, Autodesk, National Rail Enquires and others. You can sign up for the virtual agent webinar on the CRMXchange website.
Last week there was news of a chatbot developed to ferret out suspected sexual predators of underaged victims. The chatbot, called Negobot, was developed by Carlos Laorden and other academics from the University of Deusto in Bilboa, Spain. Negobot is a AIML-based conversational agent that poses as a child on Internet chat forums and social networks and employs various sophisticated methods to draw out those who exhibit pedophile behavior. Not only does Negobot use natural language processing and machine learning, but it also leverages aspects of game theory to achieve its goal of inferring if someone has a high probability of being a sexual predator.
Negobot uses an AIML structure based on the Galaia Project to find appropriate responses to questions. The chatbot was primed with pedophile conversations from an existing law enforcement database. The database of conversations is stored in English, so Negobot translates all input into English before processing. Ongoing conversations are also added to the existing database.
Applying game theory concepts, the chatter bot views each conversation in terms of seven potential levels. In each successive level, the conversational partner shows more interest in the bot. At some point, the conversation transitions to one where sex is discussed explicitly. Negobot analyzes the ongoing dialog and is aware of the level of ‘sliminess’ of the conversation. It bases its responses on this knowledge and adjusts its strategy based on the level, all the while continuing to play the game of drawing out more information and damning conversational evidence from the suspected predator.
Negobot assigns a pedophile probability to the dialog partner based on the substance of the conversation. If the other person tries to end the conversation once it becomes clear that Negobot, or rather the child it’s posing as, is underage, then the probability of pedophile behavior decreases. If the person continues to ask questions of a sexual nature, the probability increases and Negobot poses questions to discover more personal information.
Laorden and his colleagues haven’t deployed Negobot into the real world yet, but they’re continuing to refine the chatbot. It may not be long before would-be sexual predators are being ensnared by virtual agent technologies. A full discussion of Negobot’s technology and capabilities is described in an abstract about the conversational agent published by the creators.
Speech Technology Magazine reported on a new product partnership that could make it easier for you to talk to your robotic vacuum cleaner and control your air conditioner with voice commands. Conexant Systems announced that it will integrate its Far-Field Voice Input technology into home appliances manufactured by LG Electronics. The press release explains that Conexant’s voice processing input solution will provide the speech input signals to power voice controls for LG appliances.
We’ve already seen LG’s voice activated TV remote. An article published earlier this year in the Daily Mail described LG’s Roboking, a sleek robot vacuum that can be controlled with basic voice commands and clapping.
It remains to be seen how the Conexant and LG partnership will improve the voice interactions we have with our home appliances. Earlier this week, we looked at Honda Motor Corporation’s Asimo and some of its communicative shortcomings. Based on Asimo’s performance, service robots and robotic appliances still have a long way to go to catch up with the conversational abilities of the best customer service virtual agents. Perhaps we’ll see other partnerships in the future that will bring about the merger of robotics and virtual agent technologies to bring us smart appliances we can really talk to.
How about an appliance that can answer our questions about how to operate it or that can assist in troubleshooting a problem it’s having? The possibilities are limitless. I just dread the day when my refrigerator starts counting my calories out loud. That’s a talking appliance I can do without!
Last week the Verge ran an article on Honda Motor Co.’s Asimo robot. Asimo is a talking, and supposedly interactive, robot and it recently started a new job as a museum guide. Apparently Asimo failed to impress as it sought to entertain a museum audience and accompanying reporters. Ceiling sensors help the robot detect where crowds are gathering and who is raising their hand to ask a question. But Asimo ran into a problem when guests lifted their smartphones to snap photos. It mistook the gesture as hand raising and responded by blurting out the pre-programmed question “Who wants to ask Asimo a question?”
The awkwardness of the situation was only made worse by the fact that Asimo lacks voice recognition capability. You can’t actually ask Asimo a question. Instead you have to select from a set of pre-existing questions on a touch panel. Responses to the questions are pre-recorded, very much like with a traditional chatbot.
As advanced as Asimo is with many of its physical capabilities, its recent stint as museum guide highlighted apparent shortcomings. Asimo is obviously not a conversational robot. It does seem a bit odd that, considering how far voice recognition and virtual agent / dialog technologies have come in the past few years, Asimo’s product managers couldn’t have upgraded the robot with true conversational capabilities.
The lackluster response to Asimo’s performance also highlights how far our expectations have come with regard to non-human conversational partners. Being so accustomed to smartphone apps that understand us, we naturally expect smart-looking robots to know what we’re saying. If you’re responsible for customer engagement or support at your company, the pressure is on. Consumers have been conditioned to expect a lot from the technologies that seek to replace human support agents. We shouldn’t be lulled into believing that we can replace a live person with a pre-programmed, non-responsive chatbot and not have customers revolt. If a robot, a virtual agent, or any other technology is supposed to be serving us, we expect to be understood. “Who wants to ask a question?” is not going to cut it.
SpeechTek 2013 is scheduled to take place from August 19-21 at the New York Marriott Marquis in New York City. This looks like an interesting conference for anyone interested in speech technologies, virtual agents, and personal digital assistants. The conference offers four tracks: Business Strategies, Voice Interaction Design, Customer Experiences, and Technology Advances.
The SpeechTek 2013 Business Strategies track focuses on how voice technology, web self-service and other related technologies can be leveraged to provide competitive advantage and improved customer service. The Voice Interaction Design track is geared toward application developers and offers technical tracks on designing, building, and testing applications that use voice technologies and natural language processing. The Customer Experiences sessions focus on using speech recognition and web self-service to improve customer interactions and gain valuable insights into customer behavior. Technology Advances is forward-looking and examines the latest breakthroughs in voice and virtual agent technologies.
SpeechTek 2103 looks like three full days of great information and knowledge sharing on on all the key areas related to the topic of virtual agents. Whether you attend or not, you can follow the action using hashtag #SpeechTek on Twitter.