Utilization of location and environment to improve recognition

• US 10,181,321 B2
• Filed: 09/27/2016
• Issued: 01/15/2019
• Est. Priority Date: 09/27/2016
• Status: Active Grant

• Current Assignee: Vocollect, Inc. (Honeywell International Inc.)
• Original Assignee: Vocollect, Inc. (Honeywell International Inc.)
• Inventors: Miller, Kurt Charles, McNair, Arthur, Sanchez, Vanessa Cassandra, Russell, Philip E., Strane, Allan
• Primary Examiner(s): Vo, Huyen
• Application Number:
  US15/277,278
• Publication Number:
  US 20180090134A1
• Time in Patent Office: 840 Days
• Field of Search: 704233, 704246, 704231
• CPC Class Codes: G10L 13/02 Methods for producing synthetic speech; Speech synthesisers
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/226 using non-speech characteristics
• CPC Class Codes: G10L 21/0232 Processing in the frequency domain
• CPC Class Codes: G10L 21/0316 by changing the amplitude
• CPC Class Codes: G10L 21/0364 for improving intelligibility

Abstract

A portable terminal has a network interface that receives a set of instructions having a sequence of at least one location and audio properties associated with the at least one location from a server. An audio circuit receives audio signals picked up by a microphone and processes the audio signals in a manner defined by the audio properties associated with the at least one location. A speech recognition module receives processed signals from the audio circuit and carries out a speech recognition process thereupon.

Claims

1. A portable terminal, comprising:

a wireless network interface configured to receive, from a server, a set of instructions comprising at least one location, a set of actions to be carried out by a user at the at least one location, and a set of audio processing parameters associated with the at least one location;

a speech synthesizer configured to synthesize a speech command to proceed to the at least one location;

an audio circuit configured to receive audio signals picked up by a microphone and processes the audio signals;

a speech recognition module configured to receive processed signals from the audio circuit and carry out a speech recognition process thereupon to confirm arrival of the user at the at least one location; and

a processor configured to, in response to the speech recognition module carrying out the speech recognition process to confirm the arrival of the user at the at least one location, load the set of audio processing parameters associated with the at least one location, so that speech signals received from the microphone are processed using the set of audio processing parameters associated with the at least one location.

2. The terminal according to claim 1, where audio signals picked up by the microphone are stored and conveyed to a server.

3. The terminal according to claim 1, where the speech recognition module utilizes a user template that characterizes speech of a particular user to enhance recognition accuracy.

4. A method of processing speech signals at a portable terminal, comprising:

receiving a set of instructions from a server, the set of instructions comprising at least one location, a set of actions to be carried out at the at least one location, and a set of audio processing parameters associated with the at least one location;

synthesizing a speech command to proceed to the at least one location;

receiving a speech signal from a microphone confirming arrival at the at least one location;

loading the audio processing parameters associated with the at least one location; and

processing speech signals received from the microphone using the audio processing parameters associated with the at least one location.

5. The method according to claim 4, where audio signals picked up by the microphone are stored.

6. The method according to claim 4, where the speech recognition module utilizes a user template that characterizes speech of a particular user to enhance speech recognition accuracy.

7. The method according to claim 4, where the audio processing parameters include an amplifier gain, and where the amplifier gain establishes the gain of an amplifier that amplifies signals from the microphone.

8. The method according to claim 4, further comprising comparing audio signals received at the microphone with a noise model defined by the audio processing parameters, and where the audio from the microphone is discarded if the audio matches the noise model.

9. The method according to claim 4, where the audio processing parameters include at least one of a compression value, and a frequency response parameter that processes signals from the microphone.

10. The method according to claim 4, where the audio properties for the at least one location are loaded after receiving a confirmation that the terminal has arrived at the at least one location.

11. A method of processing speech signals at a portable terminal, comprising:

receiving a set of instructions from a server, the set of instructions comprising at least one location, a set of actions to be carried out at the at least one location, and a set of audio processing parameters associated with the at least one location;

synthesizing a speech command to proceed to the at least one location;

receiving a speech signal from a microphone confirming arrival at the at least one location;

loading, in response to the receiving of the speech signal from the microphone confirming arrival at the at least one location, the audio processing parameters associated with the at least one location; and

then processing speech signals received from the microphone using the audio processing parameters associated with the at least one location.

12. The method according to claim 11, where audio signals picked up by the microphone are stored.

13. The method according to claim 11, where the speech recognition module utilizes a user template that characterizes speech of a particular user to enhance speech recognition accuracy.

14. The method according to claim 11, where the audio processing parameters include an amplifier gain, and where the amplifier gain establishes the gain of an amplifier that amplifies signals from the microphone.

15. The method according to claim 11, further comprising comparing audio signals received at the microphone with a noise model defined by the audio processing parameters, and where the audio from the microphone is discarded if the audio matches the noise model.

16. The method according to claim 11, where the audio processing parameters include at least one of a compression value, and a frequency response parameter that processes signals from the microphone.

17. The method according to claim 11, where the audio properties for the at least one location are loaded after receiving a confirmation that the terminal has arrived at the at least one location.