Transcriptional dictation

• US 20080091694A1
• Filed: 08/21/2007
• Published: 04/17/2008
• Est. Priority Date: 08/21/2006
• Status: Active Grant

• Current Assignee: Unifiedvoice Corporation
• Original Assignee: Unifiedvoice Corporation
• Inventors: Harter, F., Sternklar, Daniel, Johnson, Brigham
• Granted Patent: US 8,275,613 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/68 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/088 Word spotting

Abstract

A method of dictation in which authors may assign their own words or phrases (UnifiedWords) to introduce various subjects/document elements in a document to be dictated. Each element is terminated with an ending word such as “end-it”. After transcription the UnifiedWords, with associated dictated text, are automatically recognized as introducing data that may then be processed by a backend database or program. Each author is identified in a user base and all dictation applications are associated with appropriate owner authors. Dictation applications can be created for one document, a plurality of documents including integration with respective file access methods to update specific information such as electronic medical records, legal case files, law enforcement investigative reports, and other resource databases. All methods of transcription are supported.

Claims

1. A method of organizing orally dictated information, said method comprising steps of:

creating a database of key words or phrases having special meaning, some of said key words or phrases being designated to introduce information pertaining to respective specific subjects and at least one of said key words or phrases indicating an end of said information;

making a recording of words spoken by a user, wherein the words include some of said key words and also information pertaining to said subjects;

transcribing said recording into a text file;

analyzing said text file and storing said information in a database by subject according to the introductory key words.

2. The method of claim 1, wherein the user can use his own expressions as introductory key words.

3. The method of claim 1, wherein standard keywords for a particular industry are loaded into the database from a text document or list.

4. The method of claim 3, wherein the user can modify or add to the standard keywords after they have been loaded in the database.

5. The method of claim 4, wherein the user can dictate modified subjects in random order.

6. The method of claim 1, further comprising a step of generating a report in a predetermined format from the information in the database.

7. The method of claim 3, wherein the loading of multiple text documents or lists results in one dictation session that produces multiple outputs and database stores by author, subject and multiple outputs.