Keyboard apparatus and method with voice recognition

• US 5,874,939 A
• Filed: 12/10/1996
• Issued: 02/23/1999
• Est. Priority Date: 12/10/1996
• Status: Expired due to Fees

• Current Assignee: Motorola, Inc. (Motorola Solutions, Inc.)
• Original Assignee: Motorola, Inc. (Motorola Solutions, Inc.)
• Inventors: Galvin, Christopher B.
• Primary Examiner(s): Mengistu, Amare
• Assistant Examiner(s): Osorio, Ricardo
• Application Number:
  US08/762,510
• Time in Patent Office: 805 Days
• Field of Search: 345/156, 345/157, 345/168, 704/235
• US Class Current: 345/156
• CPC Class Codes: G06F 3/023 Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A standalone keyboard (101) for use with computers (102), which keyboard (101) has integral voice recognition capabilities to facilitate both text entry and cursor-movement control. The speech recognition platform (204) may be speaker dependent and/or trainable. The keyboard (101) may have an optional display (112) to facilitate certain training activities. Recognized words are converted (206) in the keyboard (101) into keystroke data that corresponds to keystroke data as would have been output had the corresponding text been entered by an operator using the keyboard keys (107).

Claims

1. In a text entry device having a voice input and voice recognition means, a method comprising the steps of:

receiving a spoken word from an operator by means of the voice input;

failing by the voice recognition means to recognize the spoken word to within a predetermined degree of accuracy;

selecting a most likely candidate word for the spoken word;

alerting the operator of the most likely candidate word;

receiving from the operator one of;

a confirmation indicating acceptance of the most likely candidate word; and

an alternate word indicating rejection of the most likely candidate word;

if the confirmation is received from the operator, converting the most likely candidate word into keystroke data representing the constituent characters of the most likely candidate word;

if the alternate word is received from the operator, converting the alternate word into keystroke data representing the constituent characters of the alternate word; and

outputting the keystroke data.

2. The method of claim 1 wherein the step of alerting the operator comprises displaying the text by means of an alphanumeric display.

3. The method of claim 1 wherein the step of alerting the operator comprises audibly outputting the text by means of an audio enunciator.

4. The method of claim 1 wherein the step of converting the alternate word into keystroke data comprises the steps of:

storing the first spoken word in a memory; and

storing the alternate word in the memory.