Hybrid speech data processing in a vehicle

• US 10,186,269 B2
• Filed: 04/18/2016
• Issued: 01/22/2019
• Est. Priority Date: 04/18/2016
• Status: Active Grant

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Yuan, Alvin T.
• Primary Examiner(s): Opsasnick, Michael N
• Application Number:
  US15/131,615
• Publication Number:
  US 20170301351A1
• Time in Patent Office: 1,009 Days
• Field of Search: 7042701
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

A computer-implemented method for hybrid speech data processing in a vehicle includes receiving a first speech input at an input device in the vehicle and digitizing the first speech input into packets. The method includes storing the packets at a memory for predetermined amount of time and transmitting the packets using a wireless voice communication channel to a speech recognition server. Upon detecting a speech recognition condition is met associated with the packets or the wireless voice communication channel, the method includes converting one or more of the packets stored at the memory into text data and transmitting the text data using a wireless data communication channel to an interactive voice response system. Further, the method includes receiving a speech recognition result from the interactive voice response system and outputting the speech recognition result in the vehicle using an output device.

Claims

1. A computer-implemented method for hybrid speech data processing in a vehicle, comprising:

receiving a first speech input at an input device in the vehicle;

digitizing the first speech input into packets;

storing the packets at a memory for predetermined amount of time;

transmitting the packets to a speech recognition server using a wireless voice communication channel between the vehicle and the speech recognition server;

upon detecting a speech recognition condition is met associated with the packets or the wireless voice communication channel, converting one or more of the packets stored at the memory into text data, the speech recognition condition including the wireless voice communication channel being disabled, being disconnected, being timed out, having poor quality, having slow data transmission speeds or having a connection failure, the one or more of the packets including a portion of the packets lost in the transmitting the packets using the wireless voice communication channel because of the connectivity issue;

transmitting the text data using a wireless data communication channel, which is different from the wireless voice communication channel, to an interactive voice response system;

receiving a speech recognition result from the interactive voice response system; and

outputting the speech recognition result in the vehicle using an output device.

2. The computer-implemented method of claim 1, wherein converting the one or more of the packets includes converting the one or more of the packets of the first speech input received by the input device after detecting the speech recognition condition.

3. The computer-implemented method of claim 1, wherein converting the one or more of the packets includes converting the one or more of the packets of the first speech input received by the input device prior to detecting the speech recognition condition and received by the input device after detecting the speech recognition condition.

4. The computer-implemented method of claim 1, wherein the wireless voice communication channel and the wireless data communication channel are established using cellular communication network.

5. The computer-implemented method of claim 1, wherein the wireless data communication channel is established using non-cellular wireless communication.

6. The computer-implemented method of claim 1, wherein the interactive voice response system converts the text data to speech data and transmits the speech data to a third party for speech recognition processing.

7. The computer-implemented method of claim 1, wherein the speech recognition condition is based on cellular plan usage, the cellular plan associated with the vehicle.

8. A system for hybrid speech data processing in a vehicle, comprising:

a vehicle computing device including an input device, an output device, and a communication interface, each of which are operably connected for computer communication to the vehicle, wherein the input device receives a first speech input in the vehicle and the vehicle computing device digitizes the first speech input into packets; and

a network interface controller of the communication interface, where the network interface controller transmits the packets to a server for speech recognition processing using a first communication channel established between the vehicle and the server for speech recognition processing and using a cellular communication network,

wherein the server is operably connected for computer communication to the vehicle computing device, the network interface controller detects a speech recognition condition associated with the packets or the first communication channel and the communication interface converts a portion of the packets into text data,

wherein the network interface controller transmits the text data using a second communication channel, which is different from the first communication channel and established using the cellular communication network, to the server for speech recognition processing and receives a speech recognition result from the server,

wherein the output device outputs the speech recognition result in the vehicle,

wherein the speech recognition condition includes the wireless voice communication channel being disabled, being disconnected, being timed out, having poor quality, having slow data transmission speeds or having a connection failure, and

wherein the portion of the packets converted into the text data includes a portion of the packets lost in a transmission of the packets using the first communication channel because of the connectivity issue.

9. The system of claim 8, including a memory operably connected for computer communication to the vehicle, wherein the communication interface stores the packets into the memory for a predetermined period of time.

10. The system of claim 9, wherein the portion of the packets includes one or more of the packets of the first speech input received by the input device prior to detecting the speech recognition condition and received by the input device after detecting the speech recognition condition.

11. The system of claim 8, wherein the network interface controller transmits the text data using the second communication channel established using the cellular communication network to an interactive voice response system.

12. The system of claim 11, wherein the interactive voice response system converts the text data into speech data and transmits the speech data to a third party for speech recognition processing.

13. The system of claim 8, wherein the first communication channel is a voice channel and the second communication channel is a data channel.

14. The system of claim 8, wherein the speech recognition result from the server is based on a context from the text data and previously analyzed speech recognition results.

15. A non-transitory computer readable medium with instructions for hybrid speech data processing in a vehicle, the instructions for execution by a processor, comprising:

receiving a first speech input at an input device in the vehicle;

digitizing the first speech input into packets;

storing the packets at a memory for a predetermined amount of time;

transmitting the packets to a speech recognition server using a wireless voice communication channel between the vehicle and the speech recognition server;

detecting a speech recognition condition is met associated with the packets or the wireless voice communication channel and converting one or more of the packets into text data, the speech recognition condition including the wireless voice communication channel being disabled, being disconnected, being timed out, having poor quality, having slow data transmission speeds or having a connection failure, the one or more of the packets including a portion of the packets lost in the transmitting the packets using the wireless voice communication channel because of the connectivity issue;

transmitting the text data using a wireless data communication channel, which is different from the wireless voice communication channel, to an interactive voice response system;

receiving a speech recognition result from the interactive voice response system; and

outputting the speech recognition result in the vehicle.

16. The non-transitory computer readable medium of claim 15, wherein converting the one or more of the packets includes converting the one or more of the packets of the first speech input received by the input device after detecting the speech recognition condition.

17. The non-transitory computer readable medium of claim 15, wherein converting the one or more of the packets includes converting the one or more of the packets of the first speech input received by the input device prior to detecting the speech recognition condition and received by the input device after detecting the speech recognition condition.

18. The non-transitory computer readable medium of claim 15, wherein the wireless voice communication channel and the wireless data communication channel are established using a cellular communication network.

19. The non-transitory computer readable medium of claim 15, wherein the wireless data communication channel is established using non-cellular wireless communication.

20. The non-transitory computer readable medium of claim 15, wherein the speech recognition condition is based on cellular plan usage, the cellular plan associated with the vehicle.