Speech Technology - November/December 2011 - (Page 4)
VIEW FROM AVIOS
Oh, the Places You’ll Go
Speech complements fusion, multimodality, and personalization
ecently, I pondered the question: What would Dr. On one hand, speech is intuitive; on the other hand, it is Seuss have said about speech scientists in their environmentally dependent. The latter is a limiting factor in quest to achieve acceptability? What would he have written making speech the sole gateway. about “the places we have gone”—the ways in which The multimodality approach uses various communication speech applications have developed, and how far we have methods, and speech is only one of the methods. Internet and gone in trying to become mainstream? smartphone development has created a race among technoloIn the spirit of Dr. Seuss, I suggest that mainstream is not gies to compete for consumers’ hearts and minds. the right place for us. Maybe speech technology’s place is The challenge is to allow navigation and search capabilities unique and designated for applications that are otherwise quickly and comfortably, merging the touchscreen, typing, impossible. Maybe its strength is most apparent when it is and spoken word input capabilities of a smartphone. While placed side by side with other technologies. doing so, try to interpret the meaning to identify a user’s Let’s examine three nontraditional approaches in which intent and direct him to the right place. speech technologies are being used creatively as part of a When we discuss concepts like touch, talk, and type, we broader effort (as opposed to a separate module). I will let the user choose the means of interaction, and speech is illustrate the unique contribution of chosen when it best fits. Avatar customer speech and the implementation of those representatives or personal assistants are By combining speech three approaches in the industry: becoming more popular. They speak to us biometrics with 1. Fusion: Speech enhances other, naturally and interact as part of Internet recognition, you can verify the user while complementary technologies. self-service. Again, speech is one more collecting information 2. Multimodality: Speech is a means way to provide an excellent service. about his request. for a next-generation communication interface. Personalization and Customization 3. Personalization and Customization: Speech is used to Traditionally, speech has been used in call centers to maximize data and the customer experience. identify people and provide self-service. Today we use it to provide call center optimization from another interesting Fusion angle: personalization. Customer experience has been conThere are two approaches. The first is to use several analy- sidered crucial to success, and one conclusion is that cussis methods of speech algorithms together. Integrating several tomers would like to have their own personal customer technologies creates a synergy. Several areas in the industry experience. In fact, this is one of the best places for service demonstrate how speech has helped take a project to the next providers to differentiate themselves and create branding. level. By combining speech biometrics with recognition, When we personalize our IVRs, we use all the data we you can verify the user while collecting information about have to push information to customers during the dialogue his request. Another example is melding speech analytics and to ask subtly for preferences while interacting with them. with emotion detection to improve customer service. Such sophisticated dialogue requires speech technology to be The second type merges technologies. For example, secu- flexible, creative, and innovative. Those are critical qualities rity and defense applications have been using speech for when you interface with vast databases and decision-making some time now, especially for possible identification or as mechanisms because you need to consider legal and marketan indicator of a security breach. Those applications use a ing requirements, as well as an organization’s preferences. sophisticated fusion of several biometric techniques to Finally, where do we stand today with speech? Going increase confidence levels. The algorithms behind these back to Dr. Seuss, we have mountains to climb, mix-ups to fusion processes take into consideration that speech can be solve, and fears to fight. But we have opened new venues a passive form of interaction in which the speaker is not for speech technology to make a difference and influence aware that his voice is being sampled or monitored. man-machine interaction, and that’s what it’s all about.
Multimodality In speech recognition, as the complexity of an application grows, so does the need for fusion between the technologies.
Nava Shaked is the CEO of Brit Business Technologies, a call center optimization consulting company that specializes in speech technologies, and the chairperson of AVIOS Israel. She can be reached at firstname.lastname@example.org.
4 | Speech Technology
Table of Contents for the Digital Edition of Speech Technology - November/December 2011
Speech Technology - November/December 2011
View from AVIOS
Nuance and Vlingo Battle in Court
Alcatel-Lucent Unveils Mobile Capabilities for Genesys
Speech Is a Key Component of iPhone 4S
Market Spotlight: Retail
Can Voice Biometrics Hack Computer Security?
Tips for a Successful Voice Biometrics Deployment
Voice User Interface Designers Learn to Cope with Rejection
Call Recording Resolves Disputes at Medical Practice
Holly Connects IVR Pays Off for Bank
The Business Case
Speech Technology - November/December 2011