Systems and methods for concatenating electronically encoded voice

• US 20030195747A1
• Filed: 04/10/2002
• Published: 10/16/2003
• Est. Priority Date: 04/10/2002
• Status: Active Grant

• Current Assignee: Qwest Communications International Incorporated (Lumen Technologies, Inc.)
• Original Assignee: Qwest Communications International Incorporated (Lumen Technologies, Inc.)
• Inventors: Case, Eliot M.
• Granted Patent: US 7,031,914 B2
• Time in Patent Office: Days
• US Class Current: 704/223
• CPC Class Codes: G10L 13/07 Concatenation rules
• CPC Class Codes: G10L 19/09 Long term prediction, i.e. removing periodical redundancies, e.g. by using adaptive codebook or pitch predictor

Abstract

A method for concatenating a series of electronic voice segments encoded according to a source modeled algorithm is provided. The source modeled algorithm includes an excitation function such as a pitch function. The method includes evaluating an excitation function of the segments to be concatenated. The method further includes combining the segments into a sequence. The method further includes altering the excitation function such that the decoded sequence more accurately represents human speech. The alteration may include adjusting the pitch excitation function across one or more concatenation points. The alteration may also include adjusting the pitch excit across the sequence to more accurately reflect the content of the sequence. The source modeled algorithm may be a linear predictive algorithm such as Code Excited Linear Prediction (CELP) or Linear Predictive Coding (LCP). A system for concatenating a series of electronic voice segments is also provided.

Claims

1. A method of concatenating a plurality of electronic voice data segments, the plurality of segments being encoded according to a source modeled algorithm, the algorithm including at least one excitation function, wherein each data segment includes information relating to an excitation function, the method, comprising:

evaluating the plurality of electronic voice data segments;

assembling the data segments into a sequence, thereby forming at least one concatenation point;

altering the excitation function for at least one of the data segments based in part on the evaluation.

2. The method as recited in claim 1, wherein the algorithm relates to a linear predictive source modeled algorithm.

3. The method as recited in claim 1, wherein the algorithm relates to Code Excited Linear Prediction.

4. The method as recited in claim 1, wherein the algorithm relates to Linear Predictive Coding.

5. The method as recited in claim 1, wherein the excitation function relates to pitch data.

6. The method as recited in claim 1, further comprising altering the excitation function for at least one of the data segments at one of the concatenation points.

7. The method as recited in claim 1, further comprising altering the excitation function for at least one of the data segments at more than one of the concatenation points.

8. The method as recited in claim 1, further comprising developing a content-based prediction of the language represented by the sequence.

9. The method as recited in claim 8, wherein the data sequence represents a question and one of the excitation functions is related to pitch data, the method, further comprising adjusting the pitch excitation data, thereby causing the data sequence to more accurately represent a voiced question.

10. A voice data sequence, comprising:

a plurality of electronic voice data segments, each data segment being encoded according to a source modeled algorithm, wherein the plurality of data segments is joined into a consecutive sequence;

at least one concatenation point at which two of the plurality of electronic voice data segments are joined; and

at least one excitation function associated with the source modeled algorithm;

wherein one of the excitation functions is configured in part based on the content of the sequence.

11. A voice data sequence according to claim 10, wherein the data segments are encoded according to a linear predictive source modeled algorithm.

12. A voice data sequence according to claim 10, wherein the data segments are encoded according to Code Excited Linear Predictive Coding.

13. A voice data sequence according to claim 10, wherein the data segments are encoded according to Linear Predictive Coding.

14. A voice data sequence according to claim 10, wherein the excitation function that is configured in part based on the content of the sequence relates to pitch.

15. A voice data sequence according to claim 10, wherein the data sequence represents a question and one of the excitation functions relates to pitch, and wherein the pitch excitation data is configured to cause the data sequence to more accurately represent a voiced question.

16. A system for producing a sequence of concatenated electronic voice data segments, comprising:

an arrangement that selects a plurality of electronic voice data segments from a collection of electronic voice data segments, the plurality of selected segments being encoded according to a source modeled algorithm; and

a processor, configured to evaluate the plurality of electronic voice data segments;

wherein the algorithm includes at least one excitation function and each of the data segments includes information relating to the excitation function, wherein the processor is further configured to alter the excitation function for at least one of the plurality of data segments based in part on the evaluation, and wherein the processor is further configured to assemble the data segments into a sequence and cause the sequence to be transmitted to an external electronic device.

17. The system of claim 16, wherein the selected segments are encoded according to a linear predictive source modeled algorithm.

18. The system of claim 16, wherein the selected segments are encoded according to Code Excited Linear Prediction.

19. The system of claim 16, wherein the selected segments are encoded according to Linear Predictive Coding.

20. The system of claim 16, wherein the excitation function relates to pitch.