Our Partners

CBI Logo
Durham Business School
ICAEW Logo
QCA logo
 

Our partners share their knowledge and resources with M Institute so that together we can create superior information that benefits the leaders of mid-sized organisations.

Find out more about M Institute's partners.

Sound thinking on speech recognition

Speech recognition technology is helping companies improve their call centre offerings.

Progress in the accuracy of speech recognition applications has been slow since they first emerged in the 1950s, with the reliability and speed of physical interfaces such as the keyboard and mouse making them the overwhelmingly preferred methods for interacting with computers and systems. However, historical complaints of inaccuracy are no longer as valid and, due to considerable consolidation in the industry, a broad range of functionality has been made available cheaply.

The impact of the voice revolution can be seen at hotel chain Travelodge, for whom the introduction of a speech recognition-based self-service phone line has reduced the cost of telephone bookings and, crucially, allowed telephone and internet bookings to be integrated.

Of course, automated phone lines do not need to employ sophisticated speech recognition technology: touch-tone systems are still popular. However, Jason Humphries, head of EMEA professional services at speech technology vendor Nuance, believes that systems which invite the caller to speak freely and then react, rather than constraining them to limited menu options, reduce the chance of callers requesting to speak to a human operator - an option which pushes up transaction costs.

The multimodal web

Of the many emerging applications of speech recognition, it is the area of mobile Internet applications that is widely predicted to boost the importance of speech recognition technology to businesses. The size of mobile phones makes navigation awkward and speech recognition is an obvious alternative interface for directing web applications. Although it remains uncertain how this technology will work, the proposition does illustrate the 'multimodal' approach to distributing online information.

"Today, many organisations are looking to get more use from their web-based content, and to turn that material and knowledge into grammars and dialogues to use in the speech self-service world," says Art Schoeller of The Yankee Group. With web and voice services operating as two different faces of a unified system, each medium contributes to the business' knowledge base.

The burgeoning unification of web and voice channels is helped significantly by the third generation of VoiceXML, which grants voice applications native access to data used by web-based applications. Not only does the VXML standard enable two communication channels to share data, it also grants IT departments greater control over voice applications and, although in the short term this may confuse some companies, it should provide greater flexibility. Already VXML has been widely adopted as the way to do voice applications.

 For the complete article on speech recognition, please go to the Information Age website.