Most UK law firms are very familiar with the two-step dictation process where an author dictates and a secretary manually transcribes. Current digital technology has significantly reduced document completion time by allowing files to be seamlessly shared across a wide network of authors and typists. Speech Recognition is now poised to add another level of speed and greater efficiency to the process.
In the 1990s early versions of Speech Recognition failed to gain wide acceptance because computer technology was not robust enough to obtain a good result. By the early years of this century things had changed. Most legal practitioners had powerful PCs sitting on their desks, but with a booming economy and a buoyant legal market, they did not see the need to invest in cost-saving technologies. While most firms moved on from analogue to digital dictation, Speech Recognition slowly receded into the background, perceived as a technology that simply didn't deliver what it had promised.
Today, both Speech Recognition and the way legal practices operate have changed dramatically. With pressure increasing on several fronts, forward-looking firms now understand the vital role that new technologies can play in helping them gain a competitive edge. The use of Speech Recognition is increasing as a result, with firms realising how it can dramatically reduce the cost of dictations and release support staff to do more productive work.
A perfect illustration of the increased efficiency Speech Recognition can offer is the transcription of case notes. Some firms are now using SR for all of their notes, a task which comprises up to 30% of a firm's total text requirement. The notes are typed automatically as the author speaks and are quickly saved as a completed document.
Speech Recognition can also make the problems associated with staff absences a thing of the past. Authors with access to SR no longer face delays when a typist is absent and can continue to complete documents efficiently even when support staff are ill or on holiday.
The flexibility of SR also provides an extremely efficient process. A hosted speech recognition service streams recognition results back to the user's PC in real time. This ensures that documents can be reviewed, revised and completed without any delay.
Although early adopters were put off using SR by reports of poor word translation or disruption from background noise, technology has now overcome both of those barriers. The foundation of today's SR systems is a comprehensive UK dictionary that includes specialist legal terminology. By storing the users' speech and dictation patterns in its memory, the system’s word accuracy quickly improves.
Even though the advantages of SR are obvious, the current challenge for SR providers is getting legal practitioners to take a second look. Easy to install and use, it’s a technology that can offer legal professionals low start-up costs, measurable on-going cost savings and no requirement for investment in technical infrastructure or hardware. How quickly has the legal industry responded?
The pace of the move to new ways of working is quickening and those who've adopted future-proof technologies like SR report that they are reaping the benefits of greater productivity and cost-efficiency. The process will only accelerate because legal practitioners are actively sourcing new ways of working in order to arm themselves against the on-going challenges of public spending cuts, price pressures and higher customer expectation.