Method and system for sequential insertion of speech recognition results to facilitate deferred transcription services

A computer system for generating data files that contain at least some transcribed speech information, comprising:

• a display device;
• a processor coupled to the display device;
• an input device coupled to the processor to allow a user to edit information displayed on the display device;
• a digital file comprising data representative of speech recognition results obtained through speech recognition processing on speech information;
• an electronic document template viewable on the display device and representing a desired format for the resultant data file the electronic document template including two or more input fields into which different portions of the speech recognition results are to be inserted;
• a sequential insertion module operable, utilizing the processor, to cause portions of the digital file to be sequentially inserted into one of the input fields of the electronic document template, wherein sequentially inserted comprises automatically inserting contents of the digital file into a selected field of the electronic document template while enabling the user to control the sequential insertion by:
• 1) enabling the user to stop the automatic inserting contents, and then select a different one of the input fields into which desired portions of the digital file are to be inserted, and then enable the user to restart the automatic inserting contents to thereby cause the desired portions of the digital file to be inserted into the different one of the input fields;
• and/or,
• 2) enabling the user to stop the automatic inserting contents, and then edit the inserted portion(s) of the digital file within the electronic document template, then restart the automatic inserting contents.

A system for facilitating deferred transcription services, comprising:

• a file server configured to store at least one digital audio file representing speech information;
• a speech recognition module configured to analyze the digital audio file to produce a speech recognition result file;
• and
• an application server configured to execute the speech recognition module and communicate the speech recognition result file to a transcription station configured for sequential insertion of the speech recognition result file, to produce resultant documents representing transcribed speech information, wherein each of said transcription stations comprises:
• a display device;
• a processor coupled to the display device;
• an input device coupled to the processor to allow editing of information displayed on the display device and control of the sequential insertion module;
• an electronic document template viewable on the display device and representing a desired format for a resultant document and including two or more input fields into which different portions of the speech recognition result file may be inserted;
• and
• a sequential insertion module operable, utilizing the transcription station processor, to cause portions of the speech recognition results file to be sequentially inserted into the electronic document template, wherein sequentially inserted comprises automatically inserting contents of the speech recognition result file into a selected field of the electronic document template while enabling a user to control the automatic inserting by:
• 1) enabling the user to stop the automatic inserting contents and then edit the inserted portion(s) of the speech recognition result file within the electronic document template and then restart the automatic inserting contents;
• and/or,
• 3) enabling the user to stop that automatic inserting contents and then select a different one of the input fields into which desired subsequent portions of the speech recognition result file are to be automatically inserted, and then restart that automatic inserting contents, to thereby cause the desired subsequent portions of the digital file to be automatically inserted into the different selected input field.

A system comprising:

• at least one server configured to send a speech recognition result file a transcription station to thereby produce a resultant data file representing at least some transcribed speech information, wherein the transcription station comprises:
• a display device;
• a processor coupled to the display device;
• an input device coupled to the transcription station processor to allow editing of information displayed on the display device and control of the sequential insertion module;
• an electronic document template viewable on the display device and representing a desired format for the resultant data file and including two or more input fields into which different portions of the speech recognition result files are to be inserted;
• and
• a sequential insertion module operable, utilizing the processor, to cause portions of the speech recognition result file to be sequentially inserted into a selected field of the electronic document template, wherein sequentially inserting comprises automatically inserting contents of the text file into a selected the electronic document template while enabling a user to control that automatic inserting by enabling the user to stop that automatic inserting of contents, and while stopped, enabling the user to:
• (1) resume the automatic inserting of contents;
• and,
• (2) either or both of:
• (a) select a different one of the input fields into which desired portions of the speech recognition results are to be automatically inserted to thereby cause the desired portions of the speech recognition results to be automatically inserted into the selected input field;
• and,
• (b) edit the previously automatically inserted contents within the electronic document template.

A method for generating an electronic document, at least some portions of which come from a transcribed data file of speech information, the method comprising:

• generating a digital file comprising data representative of speech recognition results obtained through speech recognition processing on speech information;
• sequentially inserting portions of the digital file into the electronic document;
• providing an audio file representative of the speech information;
• outputting the audio file to allow the user to hear speech information related to the portions of the digital file being sequentially inserted into the electronic document;
• synchronizing the outputting and the sequentially inserting;
• storing the resultant data file in a format that will permit the resultant data file to be viewed electronically or printed,
• wherein sequentially inserting comprises automatically inserting the digital file into particular fields within the electronic document and at least allowing the user to selectively stop both the automatic inserting step and the outputting step to allow the user to edit at least some inserted portions within the electronic document, and then enabling the user to resume the automatic inserting and the outputting after editing selected inserted portions.

A computer system for generating transcribed data files of speech information, comprising:

• a display device;
• a processor coupled to the display device;
• an input device coupled to the processor to allow editing of information displayed on the display device;
• a digital file comprising data representative of speech recognition results obtained through speech recognition processing on speech information;
• an audio file representative of the speech information,
• a sequential insertion module operable, utilizing the processor, to cause portions of the digital file to be automatically inserted into a selected document field and viewable on the display device;
• and
• an audio output control device configured to be controlled by the user to control audio output of the audio file and thereby to allow the user to hear speech information related to the portions of the digital file being automatically inserted into the document, the audio output control device being further configured to synchronize audio output of the audio file with sequential insertion of the digital file,
• wherein the automatic insertion functionality of the sequential insertion module may be controlled by the user such that the user may:
• (1) selectively stop automatically insertion and audio output of the audio file to thereby allow the user to edit the inserted portions within the document, as needed, as the portions are automatically inserted into the document;
• and
• (2) enable the user to resume the automatic insertion and audio output after editing the selected inserted portions.