Client-Side Speech Recognition

BigHand now empowers Trust’s with the greatest level of flexibility for Speech Recognition supporting both client-side and server-side Speech Recognition integrated into a single Digital Dictation platform.

Users that are configured and licensed will see an extra ‘SR’ button in the BigHand recorder. When clicked, the Dragon engine is activated and displays a text box. Clinicians can then record as they would normally, their voice will be converted into text automatically in real time and populate the text box. A variety of voice commands are available – clinicians are able to select, correct, and apply basic formatting with their voice; popular commands such as ‘scratch that’ to delete the last or selected word and ‘caps that’ to capitalise individual words are possible, amongst many others. Clinicians can also use the rich text editor to apply bold, italics or underlines, change the font or use bullet points and numbered lists.
The clinician can then send the audio file and SR text to their secretary to be drafted into a patient letter or alternatively they themselves.

The clinician can then send the audio file and SR text to their secretary to be drafted into a patient letter or alternatively they themselves can create a Word document, based on pre-defined document templates which can also pull patient demographics into the document template, alongside mthe text that was generated by client-side SR. In addition there is an inbuilt training wizard which will walk new users through creating a speech profile which will adapt to their voice patterns. Further training can be performed on an ad-hoc basis, and the system will also learn from corrections made during the recording process.