Processing speech transmitted through a network using a plurality of processing levels

• US 7,869,995 B1
• Filed: 10/29/2007
• Issued: 01/11/2011
• Est. Priority Date: 10/04/1999
• Status: Expired due to Fees

• Current Assignee: Pearson Education Incorporated (Pearson plc)
• Original Assignee: GlobalEnglish Corporation (Pearson plc)
• Inventors: Jochumson, Christopher S.
• Primary Examiner(s): Lerner; Martin
• Application Number:
  US11/926,378
• Time in Patent Office: 1,170 Days
• Field of Search: 704/201, 704/231, 704/270, 704/270.1, 704/275, 370/468, 709/233, 434/157, 434/185
• US Class Current: 704/231
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 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 19/00 Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis in musical instruments G10H
• CPC Class Codes: G10L 19/0018 Speech coding using phonetic or linguistical decoding of the source; Reconstruction using text-to-speech synthesis

Abstract

A system receives a first value and packets of encoded audio speech from a first client. The system receives a second value and packets of encoded audio speech from a second client. Based on the first value, the system services the packets of encoded audio speech from the first client using a first processing level. Based on the second value, the system services the packets of encoded audio speech from the second client using a second processing level, which is different from the first processing level.

Claims

1. A method comprising:

receiving from a first application program executing on a first client over a network a first value and a first packet of encoded audio speech;

receiving from a second application program executing on a second client over the network a second value and a second packet of encoded audio speech, wherein the second value is different from the first value;

servicing the first packet of encoded audio speech using a first level of processing based on the first value; and

servicing the second packet of encoded audio speech using a second level of processing based on the second value, wherein the first and second levels of processing are different.

2. The method of claim 1 wherein the first value is communicated via a URL.

3. The method of claim 2 wherein the servicing the second packet of encoded audio speech comprises performing speech recognition using the second level of processing.

4. The method of claim 1 wherein the servicing the first packet comprises performing speech recognition using the first level of processing.

5. The method of claim 1 comprising:

before the receiving from a first application program executing on a first client, causing display at the first client a first message, wherein the servicing the first packet of encoded audio speech comprises evaluating using the first level of processing a pronunciation accuracy of the encoded audio speech for the first message.

6. The method of claim 1 comprising wherein after the receiving from a first application program and the servicing the first packet of encoded audio speech comprises performing speech recognition on the encoded audio speech using the first level of processing, the method further comprises:

causing display at the first client a first message representative of the encoded audio speech recognized during the speech recognition.

7. The method of claim 1 wherein the first application program comprises a Web browser.

8. The method of claim 1 wherein the first value is generated by the first application program, and the second value is generated by the second application program.

9. The method of claim 1 comprising wherein after the receiving from a first application program and the servicing the first packet of encoded audio speech comprises performing speech recognition on the encoded audio speech using the first level of processing, the method further comprises:

sending a first message to the first client in response to the encoded audio speech from the first client.

10. The method of claim 9 wherein the first application program at the client converts the first message to audio data.

11. The method of claim 9 wherein the first message is in a text format.

12. The method of claim 1 wherein the servicing the first packet of encoded audio speech and the servicing the second packet of encoded audio speech occurs concurrently.

13. The method of claim 1 wherein the first application program comprises the capability to receive audio speech from a user of the first client, store the audio speech in one or more buffers in a raw uncompressed audio format, each buffer comprising a portion of the received audio speech, encode a buffer of the received audio speech before all of the audio speech is received, package the encoded buffer to receive audio speech into one or more packets to be transmitted over the Internet before all of the audio speech is received, and transmit the first packet of encoded audio speech over the Internet before all of the audio speech is received at the first client.

14. The method of claim 13 wherein the first and second value are communicated via a URL.

15. A method comprising:

receiving from a first application program executing on a first client over a network a first value, a second value, and a first packet of encoded audio speech;

receiving from a second application program executing on a second client over the network a third value, a fourth value, and a second packet of encoded audio speech;

processing the first packet of encoded audio speech using a first level of processing based on the first value;

evaluating the first packet of encoded audio speech using a first level of speech recognition based on the second value;

processing the second packet of encoded audio speech using a second level of processing based on the third value, wherein the first and second levels of processing are different; and

evaluating the second packet of encoded audio speech using a second level of speech recognition based on the fourth value.

16. The method of claim 15 wherein the first and second value are communicated via a URL.

17. The method of claim 15 wherein the first application program comprises the capability to receive audio speech from a user of the first client, store the audio speech in one or more buffers in a raw uncompressed audio format, each buffer comprising a portion of the received audio speech, encode a buffer of the received audio speech before all of the audio speech is received, package the encoded buffer to receive audio speech into one or more packets to be transmitted over the Internet before all of the audio speech is received, and transmit the first packet of encoded audio speech over the Internet before all of the audio speech is received at the first client.

18. The method of claim 17 wherein the first and second value are communicated via a URL.

19. A method comprising:

receiving from a first application program executing on a first client over a network a first value and a second value via a first URL, and a first packet of encoded audio speech;

receiving from a second application program executing on a second client over the network a third value and a fourth value via a second URL, and a second packet of encoded audio speech;

processing the first packet of encoded audio speech using a first level of processing based on the first value;

evaluating the first packet of encoded audio speech using a first level of speech recognition based on the second value;

processing the second packet of encoded audio speech using a second level of processing based on the third value, wherein the first and second levels of processing are different; and

evaluating the second packet of encoded audio speech using a second level of speech recognition based on the fourth value.