Voice recognition technology to capture geoscience data

• US 7,319,961 B2
• Filed: 03/04/2004
• Issued: 01/15/2008
• Est. Priority Date: 03/04/2004
• Status: Active Grant

• Current Assignee: Saudi Arabian Oil Company (Government of Saudi Arabia)
• Original Assignee: Saudi Arabian Oil Company (Government of Saudi Arabia)
• Inventors: Cantrell, Dave L., Al-Jallal, Ibrahim A., Al-Dhubaib, Tofig A.
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US10/794,474
• Publication Number:
  US 20050197841A1
• Time in Patent Office: 1,412 Days
• Field of Search: 704/270, 704/275
• US Class Current: 704/270
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A hands-free system for capturing data and generating reports recognizes speech as text and commands to create a set of entries intended to have a mathematical relationship to each other such that, if these entries fail to satisfy the relationship, a voice synthesizer generates a warning signal to indicate an error by the user.

Claims

1. A hands-free system for assisting in capturing data and generating a report during examination of rock samples and/or thin sections, said system being designed to include a plurality of entries, where a first number of the entries form a matrix within the report, said system comprising:

a speech input for receiving units of speech, each unit of speech being one of a command and text;

a speech recognition system connected to said input for recognizing a content of each unit of speech and for encoding each unit of speech into a respective unit of data such that, based upon the recognized content of each unit of speech, that unit of speech is identified as a command having a respective unit of command data or as text having a respective unit of text data;

a voice synthesizer for synthesizing audible speech signals, where said voice synthesizer, in response to a received one of the units of data, generates an audible speech signal representative of the recognized content of the respective unit of speech;

a control for sending selected ones of the units of data to said voice synthesizer;

a vocabulary manager for receiving each unit of text data for determining a respective entry to be included in the report in accordance with a defined first set of rules; and

a navigation manager for receiving each unit of command data for determining a course of action in generating the report in accordance with the received unit of command data and a defined second set of rules, the second set of rules including a set of identifying rules for identifying a position in the matrix of an entry when that entry is one of the first plurality of entries,

where a second plurality of the entries is defined as a subset of the first plurality of entries, the second plurality of entries being intended to have a predetermined mathematical relationship to each other,

where the first set of rules includes a rule for determining whether or not a specific entry, when the specific entry is one of the second plurality of entries, is in accordance with the predetermined mathematical relationship, and

where, when the specific entry is determined by the determining rule to be not in accordance with the predetermined mathematical relationship, said synthesizer generates a warning signal to indicate an error.

2. The system of claim 1, wherein the warning signal is an audible signal.

3. The system of claim 1, wherein the warning signal is an audible speech signal.

4. The system of claim 1, wherein the set of identifying rules includes a rule for moving a cursor from a current position in the matrix to a new position in the matrix in response to a command for moving.

5. The system of claim 4, wherein when the command for moving indicates cursor movement within the matrix by a specified amount in a specified direction of the matrix, the rule for moving moves the cursor within the matrix from the current position by the specified amount in the specified direction.

6. The system of claim 1, wherein the permissible commands include a command for creating an entry.

7. The system of claim 1, wherein the permissible commands include a command for changing an entry.

8. The system of claim 1, wherein the mathematical relation is between relative percentages indicated by the first plurality of entries.

9. The system of claim 1, wherein the first plurality of entries are the entries intended to fill one column of the matrix.

10. The system of claim 1, further comprising a classifier connected to said speech recognition system for, based upon the recognized content of each unit of speech, identifying that unit of speech as a command having a respective unit of command data or as text having a respective unit of text data.