Customer-Focused Self-Service Not an Oxymoron
"A look at the top tools and strategies to enhance the customer’s self-service experience — and open their minds to the power of automation...The latest trend takes a much more proactive and dynamic approach to assisting customers who embark on a self-service transaction. “Guided speech” IVR —a.k.a., guided IVR, agent-assisted IVR, hybrid IVR, et al. — combines the technological potency of advanced speech applications with, when necessary, the human intelligence and understanding of live agents. In centers that use Guided Speech IVR ^®, designated agents serve as invisible IVR guides —assisting the center’s speech application with recognition on an as-needed basis..."

Source: Customer Management Insight
Author: Greg Levin

Secret Agents: The hidden value of someone behind the scenes.
"Spoken Communications ^® compares its agent-assisted interactive voice response (IVR) technology to the U-Scan brand. The Seattle-based company has carved a place for itself in the crowded contact center industry by selling a single product it says solves three major IVR-related problems: hold times, opt-out rates, and speech recognition errors."

Source: Speech Technology Magazine
Author: Lauren Shopp

Hybrid Hopes - If call centers want to circumvent most speech recognition problems, the time has come for hybrid architectures.
For those considering speech-rec technologies in their call centers, the first step is to understand that it is not safe to assume the technology will approach 100 percent accuracy in recognizing human utterances in a deployed speech-enabled application...

Unfortunately, some of the most severe usability problems of speech-enabled systems result from speech recognition failures. The solution is hybrid architectures--it is now possible to remove all of the experience of speech failure from a speech-enabled IVR.

Voice solutions provider Spoken Communications ^® supports a hybrid architecture in which the speech recognizer is backed up by a human who can monitor four or more interactions at once.

Source: DestinationCRM.com and CRM Magazine
Author: Dr. Walter Rolandi

Assisted Self-Service is simpler to implement!
A basic growth limitation of speech technology in customer-facing applications is the enormous cost that is incurred to actually implement a speech-enabled self-service application. Much of this cost is devoted to figuring out how to deal with the error situations that occur. A lot of time is spent debating whether: “did you mean ….?”, or “…..is that correct?” is a better response to an error...

Despite the enormous implementation effort (cost), the present approach yields results that discourage callers from using self-service and alienates them towards the organization that is providing the self-service. Callers often prefer to use self-service, but not when it is done badly and wastes their time. Ask a caller what they think of their experience with speech and too often the response is: “I hate those things, they never recognize what I’m saying and make me repeat everything.” This is the result, despite the designers putting an enormous amount of effort into error recovery...

With Assisted Self-Service, the need to implement complex automated error recovery processes is totally eliminated. The human agents that are monitoring the progress of each of the callers, are very good at identifying just what a caller is saying, even when the caller is in noisy environment, has a strong accent or is saying something that is not in the ASR grammar...Assisted Self-Service yields better results for the caller and is significantly less costly to implement...

Source: ASR News, Volume 18, No. 2
Author: Walt Tetschner, Voice Information Associates

The Pains of Main Are Plainly VUI’s Bane
"Main Menu plays the same critical role in VUIs. Like in the fast-food example, It is where the system asks the user, “Why are you here?” and, subsequently, determines the dialogue to follow. If it asks the question and then cannot process the response properly, it is, by definition, clueless, and users quickly lose patience with a clueless system.

Of course what is missing in such dialogues is human intelligence. Barring dramatic breakthroughs in artificial intelligence, the situation for pure automation is not likely to change anytime soon...

[A] very promising, way to overcome the problems of the Main Menu is to interject human intelligence by using a hybrid system architecture. In a hybrid system, human assistants sit behind the ASR engine. The ASR engine does what it always does and dialogue proceeds as long as confidence factors are sufficiently high. The human assistant surreptitiously intervenes, however, upon ASR failure. He listens to the unrecognized utterance and then directs the interaction accordingly. Users are thus spared the frustrating experience of interaction with a system that is incapable of determining their intent. Interestingly, users are not usually aware of the human intervention and they therefore tend to think highly of the automated system."

Source: Speech Technology Magazine, SpeechTEK Buyers Guide
Author: Dr. Walter Rolandi, The Human Factor, Speech Technology Magazine

The telephone speech industry needs Assisted Self Service!
"I've become convinced that the present approach to speech-enabled self-service does not have a solid future...Spoken Communications ^® ...[is] leading the charge with promising technology [Guided Self-Service]."

Source: ASR News, Volume 18, No.1
Author: Walt Tetschner, Voice Information Associates