The Voice of the Future

NEW YORK -- One of CRM's as-yet-unfulfilled innovations--the potential inherent in speech technology as an interface to search for data--was the focus of a presentation here yesterday at SpeechTEK 2007, the sister conference to destinationCRM2007
. During a panel called "Voice Search," Leo Chiu, chief technology officer at speech technology vendor Apptera, explained the sought-after ideal: real-time performance, low recognition-error rates, and open-ended voice search. However, as Charles Galles, principal speech solutions architect at fellow vendor Intervoice, said in the same panel, that ideal is still a long way off. Parameters in speech technology are prone to aging and any voice-activated search system would require constant tuning. Tuning problems, in fact, continue to plague the technology. A voice search system, Galles told the crowd, "must be more dynamic" and engineers must be able to change search criteria and word associations "on the fly." Still, large enterprises such as IBM and Google continue to devote resources to the topic, an indication of a hopeful future for voice search. The eventual success of voice search, according to Chiu, would be, in part, a reflection of how open-ended it would have to be, thanks to a near-certain reliance on natural language. Any implementation of natural language, however, has its own problems. For instance, an uneducated end-user might approach the system as if it were capable of understanding every word--a common misstep. In another SpeechTEK 2007 panel, "Advances in Natural Language Processing," one panelist noted that any natural-language system would have to be able to parse unnecessary verbiage from consumers. Thus, a natural language interface needs to be trained on a large body of real data. At the same time, overstuffing the system with concepts would cause recognition errors. As natural language develops beyond its current embryonic state, it probably should be integrated into CRM initiatives sparingly and only in specific circumstances, such as ones that involve large item lists or that require end users to speak freely. In most cases, a simple directed dialogue interface is adequate, according to Jim Larson, vice president of Larson Technical Services. "People already know what to expect with directed dialogue," he said, adding that a sudden switch within a system to natural language could confuse end-user response and, consequently, the speech-recognition engine. And yet, even with all of these developments, Larson wondered if the industry hadn't already missed the boat. During a Q&A following the "Speech in the Mainstream" panel, Larson said he wasn't completely optimistic about the industry's future. "The iPhone was a missed opportunity," he said, regarding its lack of speech technology. This was particularly ironic, he said, because a phone would seem like the natural place to host a voice-driven interface. "Americans are just so used to a graphical user interface," he said, wondering if society would ever be willing to shift to a voice-driven one. But if the tipping point occurs, as Malcolm Gladwell stated in his destinationCRM2007/SpeechTEK 2007 keynote on Tuesday, it will probably happen quickly and unexpectedly. And, the experts suggested, it would behoove designers and developers to hone their technologies and continue developing new ones if they hope to usher it along. SpeechTEK 2007, which runs through Thursday, marks the third event since Speech Technology magazine and its events were acquired by Information Today, Inc. (ITI), CRM magazine's parent company. (The first was SpeechTEK 2006 in August 2006 and the second was SpeechTEK West in February of this year.) SpeechTEK is being co-located this time around with CRM's annual destinationCRM2007 conference, which runs through Wednesday. [CORRECTION: Due to an editing error, earlier versions of this article incorrectly attributed a quote from the panel "Advances in Natural Language Processing" to Jonathan Bloom, senior VUI designer at SpeechCycle. regrets the error.] Related articles: Feature: The Voices of Reason Speech technology experts reveal the value of analytics and the secrets of locating what your customers say about you. CRM at the Tipping Point The renowned author of The Tipping Point and Blink speaks at destinationCRM2007 about how CRM can break the barrier and make its way to success. The Price is Right: Price Optimization 101 A session on the emerging technology kicks off the destinationCRM2007 conference in New York, and focuses on how businesses are maximizing profitability analytics. The 2.0 Effect At destinationCRM2007, author and futurist Stan Davis outlines the influence that Web 2.0 is having on the ability to service and sell to the next generation of consumers.
CRM Covers
for qualified subscribers
Subscribe Now Current Issue Past Issues