초록 ▼

A distributed voice user interface system includes a local device which receives speech input issued from a user. Such speech input may specify a command or a request by the user. The local device performs preliminary processing of the speech input and also provides the speech input to a remote syst

A distributed voice user interface system includes a local device which receives speech input issued from a user. Such speech input may specify a command or a request by the user. The local device performs preliminary processing of the speech input and also provides the speech input to a remote system. The local device is able to update its recognition capabilities based on analysis of the speech, input by the remote system.

대표청구항 ▼

1. A method comprising: initiating a connection with a remote system upon detection by a speech recognition operation of a local system of a keyword in a speech input;storing a portion of the speech input into a local memory at the local system;transmitting the stored portion of the speech input fro

1. A method comprising: initiating a connection with a remote system upon detection by a speech recognition operation of a local system of a keyword in a speech input;storing a portion of the speech input into a local memory at the local system;transmitting the stored portion of the speech input from the local system to the remote system; andupdating or modifying a set of recognizable keywords stored by the local system based on updates or modifications received from the remote system responsive to analysis of the stored portion of the speech input performed by a speech recognition operation of the remote system. 2. The method of claim 1, further comprising: scanning the transmitted portion at the remote system for one or more keywords. 3. The method of claim 1, further comprising: receiving a control signal from the remote system, the control signal configured to trigger speech generation; andoutputting generated speech from the triggered speech generation. 4. The method of claim 1, further comprising: receiving generated speech from the remote system; andoutputting the generated speech. 5. The method of claim 1, wherein initiating the connection with the remote system comprises scanning speech input issued by a user at a local device. 6. The method of claim 5, wherein transmitting the stored portion of the speech input to the remote system comprises transmitting the stored portion of the speech input from the local device to the remote system. 7. The method of claim 1, further comprising; storing a record comprising one or more resources utilized in responding to the speech input. 8. The method of claim 7, wherein the record comprises charges incurred in responding to the speech input. 9. The method of claim 1, wherein analysis of the stored portion of the speech input by the remote system comprises analysis of language usage or acoustic properties of a voice. 10. The method of claim 1, wherein updating or modifying the set of recognizable keywords comprises updating or modifying the set of recognizable keywords in response to a user request. 11. A computer-readable medium having computer program logic recorded thereon, execution of which, by a computing device, causes the computing device to perform operations comprising: initiating a connection with a remote system upon detection, by a speech recognition operation of a local system, of a keyword in a speech input;storing a portion of the speech input into a local memory at the local system;transmitting the stored portion of the speech input from the local system to the remote system; andupdating or modifying a set of recognizable keywords stored by the local system based on updates or modifications received from the remote system responsive to analysis of the stored portion of the speech input performed by a speech recognition operation of the remote system. 12. The computer-readable medium of claim 11, the operations further comprising: scanning the transmitted portion at the remote system for one or more keywords. 13. The computer-readable medium of claim 11, the operations further comprising: receiving a control signal from the remote system, the control signal configured to trigger speech generation; andoutputting generated speech from the triggered speech generation. 14. The computer-readable medium of claim 11, the operations further comprising: receiving generated speech from the remote system; andoutputting the generated speech. 15. The computer-readable medium of claim 11, wherein initiating the connection with the remote system comprises scanning speech input issued by a user at a local device. 16. The computer-readable medium of claim 15, wherein transmitting the stored portion of the speech input to the remote system comprises transmitting the stored portion of the speech input from the local device to the remote system. 17. The computer-readable medium of claim 11, the operations further comprising: storing a record comprising one or more resources utilized in responding to the speech input. 18. The computer-readable medium of claim 17, wherein the record comprises charges incurred in responding to the speech input. 19. The computer-readable medium of claim 11, wherein analysis of the stored portion of the speech input by the remote system comprises analysis of language usage or acoustic properties of a voice. 20. The computer-readable medium of claim 11, wherein updating or modifying the set of recognizable keywords comprises updating or modifying the set of recognizable keywords in response to a user request. 21. A system comprising: a speech recognition module configured to detect a keyword in a speech input; one or more memory devices configured to store a portion of the speech input; a transceiver configured to initiate a connection with a remote system upon detection, by the speech recognition module, of the keyword and to transmit the stored portion of the speech input to the remote system; andan updating module configured to update or modify a set of recognizable keywords stored by the one or more memory devices based on updates or modifications received from the remote system responsive to analysis of the stored portion of the speech input performed by a speech recognition operation of the remote system. 22. The system of claim 21, wherein the remote system is configured to scan the transmitted portion for one or more keywords. 23. The system of claim 21, wherein the transceiver is configured to receive a control signal from the remote system, the control signal configured to trigger speech generation, further comprising: an audio module configured to output generated speech from the triggered speech generation. 24. The system of claim 21, wherein the transceiver is configured to receive generated speech from the remote system, further comprising: an audio module configured to output the generated speech. 25. The system of claim 21, wherein detecting the keyword in the speech input comprises scanning speech input issued by a user at a local device. 26. The system of claim 25, wherein transmitting the stored portion of the speech input to the remote system comprises transmitting the stored portion of the speech input from the local device to the remote system. 27. The system of claim 21, wherein the is one or more memory devices are further configured to store a record comprising one or more resources utilized in responding to the speech input. 28. The system of claim 27, wherein the record comprises charges incurred in responding to the speech input. 29. The system of claim 21, wherein analysis of the stored portion of the speech input by the remote system comprises analysis of language usage or acoustic properties of a voice. 30. The system of claim 21, wherein the updating module is configured to update or modify the set of recognizable keywords in response to a user request.