Aircraft speech recognition and voice training data storage and retrieval methods and apparatus

• US 8,370,157 B2
• Filed: 07/08/2010
• Issued: 02/05/2013
• Est. Priority Date: 07/08/2010
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Boregowda, Lokesh Rayasandra, Jayaprakash, Meruva, Sinha, Koushik
• Primary Examiner(s): Smits, Talivaldis Ivars
• Application Number:
  US12/832,651
• Publication Number:
  US 20120010887A1
• Time in Patent Office: 943 Days
• Field of Search: None
• US Class Current: 704/270
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/07 to the speaker
• 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

Abstract

A speech recognition system and a personal speech profile data (PSPD) storage device that is physically distinct from the speech recognition system are provided. In the speech recognition system, a PSPD interface receives voice training data, which is associated with an individual and the operating conditions of an aircraft, from the PSPD storage device. A speech input module produces a digital speech signal derived from an utterance made by a system user. A speech processing module accesses voice training data stored on the PSPD storage device through the PSPD interface, and executes a speech processing algorithm that analyzes the digital speech signal using the voice training data, in order to identify one or more recognized terms from the digital speech signal. A command processing module initiates execution of various applications based on the recognized terms. Embodiments may be implemented in various types of host systems, including an aircraft cockpit-based system.

Claims

1. A speech recognition system of an aircraft comprising:

a personal speech profile data (PSPD) interface configured to receive voice training data, which is associated with an individual, from a PSPD storage device that is physically distinct from the speech recognition system;

a speech input module configured to produce a digital speech signal derived from an utterance made by a system user; and

a speech processing module, operatively coupled to the speech input module, and configured to selectively retrieve the voice training data stored on the PSPD storage device through the PSPD interface based on operating condition parameters of the aircraft and a characteristic of the system user, and to execute a speech processing algorithm that analyzes the digital speech signal using the voice training data, in order to identify one or more recognized terms from the digital speech signal.

2. The speech recognition system of claim 1, further comprising:

a voice training data cache, operatively coupled between the speech processing module and the PSPD interface, and configured to receive the voice training data from the PSPD interface and to provide access to the voice training data to the speech processing module.

3. The speech recognition system of claim 1, wherein the PSPD interface is selected from a group consisting of a memory card reader, a contact smartcard reader, a contactless smartcard reader, a memory stick reader, a secure digital (SD) card reader, a multimedia card reader, a subscriber identity module (SIM) card reader, a universal serial bus (USB) interface, a compact disc reader, a Bluetooth interface, a wireless communications interface, and a headset interface.

4. The speech recognition system of claim 1, further comprising the PSPD storage device, which comprises:

a speech recognition system interface configured to interact with the PSPD interface in order to provide access to the voice training data to the speech processing module; and

data storage, operatively coupled with the speech recognition system interface, and configured to store the voice training data.

5. The speech recognition system of claim 4, wherein the PSPD storage device is selected from a group consisting of a memory card, a contact smartcard, a contactless smartcard, a memory stick, a secure digital (SD) card, a multimedia card, a subscriber identity module (SIM) card, a universal serial bus (USB) flash drive, a compact disc, a Bluetooth device, a wireless communications device, and a storage device integrated with a headset.

6. The speech recognition system of claim 4, wherein the speech recognition system further comprises a user identity verification module, operatively coupled with the PSPD interface, and configured to collect a biometric sample from the system user, to access biometric data associated with the individual from the PSPD storage device through the PSPD interface, and to grant access to the speech recognition system to the system user when a sufficient correlation is present between the biometric sample and the biometric data.

7. The speech recognition system of claim 4, wherein the speech recognition system further comprises a user identity verification module, operatively coupled with the PSPD interface, and configured to enable the system user to provide an entered personal identification number (PIN), to access a valid PIN associated with the individual from the PSPD storage device through the PSPD interface, and to grant access to the speech recognition system to the system user when the entered PIN and the valid PIN match.

8. The speech recognition system of claim 4, wherein the PSPD storage device further comprises a voice training data update module, operatively coupled to the PSPD interface, and configured to generate updated voice training data based on the digital speech signal, and to provide the updated voice training data to the PSPD storage device through the PSPD interface.

9. The speech recognition system of claim 1, further comprising:

a command processing module, operatively coupled to the speech processing module, and configured to determine a system response based on the one or more recognized terms, and to generate one or more control signals to cause a host system coupled to the speech recognition system to implement the system response.

10. The speech recognition system of claim 9, wherein the host system is selected from a group consisting of, an aircraft control system, a spacecraft control system, an air traffic control (ATC) system, an electronic records system, a robotics system, a hardware system control and monitoring system, a computer system control and monitoring system, a network control and monitoring system, a portable system used for emergency search and rescue operations, and an industrial monitoring and control system.

11. The speech recognition system of claim 9, wherein the host system is an aircraft control system, and the command processing module is configured to generate the one or more control signals to cause the aircraft control system to affect operation of one or more aircraft subsystems selected from a group of subsystems consisting of a radio communication module, a graphics and display system, a control surface actuation module, a landing gear actuation module, a cabin environment control system, a throttle control system, a propulsion system, a radar system, and a data entry system.

12. A portable data storage device comprising:

data storage configured to store voice training data associated with an individual and operating conditions of an aircraft; and

a speech recognition system interface, operatively coupled with the data storage, and configured to interact with a portable data storage device interface of a speech recognition system of an aircraft in order to provide access to the voice training data to the speech recognition system of an aircraft, wherein the portable data storage device is physically distinct from the portable data storage device interface and the speech recognition system, and

wherein the data storage is further configured to store a personal identification number (PIN) associated with the individual, and wherein the speech recognition system interface is further configured to interact with the portable data storage device interface of the speech recognition system in order to provide access to to perform verification of the pilot using the PIN.

13. The portable data storage device of claim 12, wherein the data storage device is selected from a group consisting of a memory card, a contact smartcard, a contactless smartcard, a memory stick, a secure digital (SD) card, a multimedia card, a subscriber identity module (SIM) card, a universal serial bus (USB) flash drive, a compact disc, a Bluetooth device, a wireless communications device, and a storage device integrated with a headset.

14. The portable data storage device of claim 12, wherein the data storage is further configured to store biometric data associated with the individual, and wherein the speech recognition system interface is further configured to interact with the portable data storage device interface of the speech recognition system in order to provide access to the biometric data.

15. The portable data storage device of claim 12, further comprising:

a voice training data update module, operatively coupled to the speech recognition system interface, and configured to receive updated voice training data from the speech recognition system through the speech recognition system interface, and to store the updated voice training data in the data storage.

16. A method for performing speech processing on an aircraft, the method performed by a speech recognition system and comprising the steps of:

selectively retrieving voice training data, which is associated with an individual, from a personal speech profile data (PSPD) storage device that is physically distinct from the speech recognition system based on operating condition parameters of the aircraft and characteristics of the individual;

producing a digital speech signal based on an utterance made by a system user; and

executing a speech recognition algorithm that analyzes the digital speech signal using the voice training data, in order to identify one or more recognized terms from the digital speech signal.

17. The method of claim 16, further comprising:

collecting identity-indicating information from the system user;

accessing user identity verification information, which is associated with the individual, from the PSPD storage device, wherein the user identity verification information is selected from a group consisting of biometric data and a personal identification number (PIN);

performing an identity verification process to determine whether a correlation exists between the identity-indicating information and the user identity verification information; and

granting access to the speech recognition system to the system user when a sufficient correlation is present between the identity-indicating information and the user identity verification information.

18. The method of claim 16, further comprising:

determining a system response based on the one or more recognized terms; and

generating one or more control signals to cause a host system coupled to the speech recognition system to implement the system response.

19. The method of claim 18, further comprising:

generating updated voice training data based on the digital speech signal; and

providing the updated voice training data to the PSPD storage device.