Device and method for determining a user-desired mode of inputting speech

• US 20070129098A1
• Filed: 12/06/2005
• Published: 06/07/2007
• Est. Priority Date: 12/06/2005
• Status: Abandoned Application

• Current Assignee: Motorola, Inc. (Motorola Solutions, Inc.)
• Original Assignee: Motorola, Inc. (Motorola Solutions, Inc.)
• Inventors: Cheng, Yan, Mazurkiewicz, Ted
• Application Number:
  US11/295,198
• Publication Number:
  US 20070129098A1
• Time in Patent Office: Days
• US Class Current: 455/550.100
• CPC Class Codes: H04M 1/72466 with selection means, e.g. keys, having functions defined by the mode or the status of the device
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00

Abstract

A device and method of detecting a mode of inputting speech to a wireless device includes a processor (220) communicatively coupled to a user input (218), an audio input (206), a timer (211), and a speech processor (230). The processor (220) monitors the user input (218) and, upon detection of a first change in state of the user input (218), opens an input channel from the audio input (206) to the speech processor (230), monitors the timer (211) for an elapsed time, and monitors the user input (218) for a second change of state. Upon detection of the second change of state after a predetermined amount of time elapses, the input channel is closed. Upon detection of the second change of state before a predetermined amount of time elapses, the user input is monitored for a third change of state and upon detecting the third change of state, the input channel is closed.

Claims

1. A wireless device comprising:

a processor for processing instructions;

a user input communicatively coupled to the processor;

an audio input communicatively coupled to the processor;

a timer communicatively coupled to the processor; and

a speech processor communicatively coupled to the processor,

wherein the processor monitors the user input and, upon detection of a first change in state of the user input, operates to;

open an input channel from the audio input to the speech processor;

monitor the timer for an elapsed time;

monitor the user input for a second change in state, and;

upon detection of the second change in state after a predetermined amount of time elapses, close the input channel; and

upon detection of the second change of state before the predetermined amount of time elapses, monitor an automatic speech-end-point detector or the user input for a third change in state, and

upon detecting the third change in state of the user input or a speech-end-point, close the input channel.

2. The wireless device according to claim 1, wherein the user input comprises a button, a keypad, or a touch screen.

3. The wireless device according to claim 1, wherein the first change of state comprises a depression of a button.

4. The wireless device according to claim 1, wherein the second change of state comprises a release of a depressed button.

5. The wireless device according to claim 1, wherein the speech processor is a software application executed in the processor.

6. A method for detecting a mode of inputting speech to a wireless device, the method comprising:

detecting a first change of state of a user input;

opening an input channel from an audio input to a speech processor;

monitoring a timer for an elapsed time;

monitoring the user input for a second change of state and;

upon detection of the second change of state occurring after a predetermined amount of time has elapsed since the first change of state was detected, closing the input channel; and

upon detection of the second change of state occurring before the predetermined amount of time has elapsed since the first change of state was detected, monitoring an automatic speech-end-point detector or the user input for a third change of state and upon detecting the third change of state of the user input or a speech-end-point, closing the input channel.

7. The method according to claim 6, wherein the user input comprises a button, a keypad, or a touch screen.

8. The method according to claim 6, wherein the first change of state comprises a depression of a button.

9. The method according to claim 6, wherein the second change of state comprises a release of a depressed button.

10. The method according to claim 6, further comprising:

receiving a speech stream at the audio input; and

processing the speech stream with the speech processor to recognize instructions.

11. A computer program product for detecting a mode of inputting speech to a wireless device, the computer program product comprising:

a storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing a method comprising;

detecting a first change of state of a user input;

opening an input channel from an audio input to a speech processor;

monitoring a timer for an elapsed time;

monitoring the user input for a second change of state and;

upon detection of the second change of state occurring after a predetermined amount of time has elapsed since the first change of state was detected, closing the input channel; and

upon detection of the second change of state occurring before the predetermined amount of time has elapsed since the first change of state was detected, monitoring an automatic speech-end-point detector or the user input for a third change of state and upon detecting the third change of state of the user input or a speech-end-point, closing the input channel.

12. The computer program product according to claim 11, wherein the user input is a button, a keypad, or a touch screen.

13. The computer program product according to claim 11, wherein the first change of state is a depression of a button.

14. The computer program product according to claim 11, wherein the second change of state is a release of a depressed button.

15. The computer program product according to claim 11, further comprising:

receiving a speech stream at the audio input; and

processing the speech stream with the speech processor to recognize instructions.