Installing Dragon NaturallySpeaking to work with the Orator Dictation System, Bytescribe Export Utility and DocShuttle Transcription Software.
In order to use Dragon NaturallySpeaking for speech recognition, you will need Dragon NaturallySpeaking Medical or Preferred Edition (that has the AutoTranscribe Folder) and Bytescribe Export Utility Version 5.0.
Step 1. Network a "Converting Computer" to the Orator Dictation System as shown in the diagram below.
Step 2. Install the Dragon NaturallySpeaking, Bytescribe Export Utility (Speech Recognition Version) and DocShuttle Administrator software on the Converting Computer.
Step 3. Create a new user profile in the Dragon software using the "Digital recorder (.wav, .mp3, .wma)" option. As you go through the wizard to set up the profile, it will require you to have a .wav file. You will need to create this .wav file by calling into the Orator dictation system and recording a training reading suggested by the Dragon wizard. Then use the Bytescribe Export Utility to convert the recorded file into a .wav file (choose Output Format: 11KHz Wav). Use this .wav file to train the user profile in Dragon. Once you have finished training this profile, close the main Dragon program.
Step 4. Open the Auto Transcribe Folder by clicking "Start | Programs | Dragon NaturallySpeaking | AutoTranscribe Folder Agent".
Step 5. Click the " + " button in the tool bar to set up a new conversion folder. You will need to specify the "Input directory", "Output directory", "Profile Name" and "Dictation Source". An example is shown below:
Input directory: C:\Dragon\Input
Output directory: C:\Dragon\Output
Dictation Source: Digital recorder (.wav, .mp3, .wma)
Step 6. From the Bytescribe Export Utility menu, select View | Options, then click the "Speech Recognition Tab". Click the "Enable speech recognition" checkbox and enter the same input and output directories as in the previous step.
Step 7. Click View | Directories from the Bytescribe Export Utility menu. Configure the Input and Output Directories for the Export Utility. The Input Directory should be the location of .vox files located in Dictation System folder (e.g. "C:\Dictation System\Type1). The Output Directory should be the location the DocShuttle software (e.g. C:\Convert\TSP\Type1). You will need to do this for each "Job Type" folder in set up in the Orator Dictation System.
Step 8. Configure the DocShuttle Administrator software with the correct FTP settings for you FTP site.
You are now ready to use the "Converting Computer" for speech recognition.
Voice files recorded in the Orator Dictation System will be sent to the Export Utility "Output Directory". The text documents transcribed by Dragon will appear in the DocShuttle "Documents" folder (usually "C:\Convert\TSP\Documents").
Once voice files are converted to text files, the voice and text files are automatically uploaded to an FTP server by DocShuttle Administrator software. They are then accessible to transcriptionists using DocShuttle transcription software.
As files are downloaded into DocShuttle Transcriptionist, the text files created by Dragon NaturallySpeaking appear in the attachments window for each voice. A screen shot as shown below.
As the transcriptionist creates a new Microsoft Word document using the Create New Document window, the transcribed text will automatically appear in the new Word document.