Optimizing call quality using vocal frequency fingerprints to filter voice calls

• US 10,825,462 B1
• Filed: 09/04/2018
• Issued: 11/03/2020
• Est. Priority Date: 02/23/2015
• Status: Active Grant

• Current Assignee: T-Mobile Innovations LLC (Deutsche Telekom AG)
• Original Assignee: Sprint Communications Company LP (Deutsche Telekom AG)
• Inventors: Drews, Gregory Anderson, Farst, Brian Dale, Lee, Young Suk, Reeves, Raymond
• Primary Examiner(s): Wozniak, James S
• Application Number:
  US16/120,877
• Time in Patent Office: 791 Days
• Field of Search: 704226, 704227, 704246, 7042701
• CPC Class Codes: G10L 19/018 Audio watermarking, i.e. embedding inaudible data in the audio signal
• CPC Class Codes: G10L 2021/0135 Voice conversion or morphing
• CPC Class Codes: G10L 21/013 Adapting to target pitch
• CPC Class Codes: G10L 21/02 Speech enhancement, e.g. noise reduction or echo cancellation reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08
• CPC Class Codes: G10L 25/18 the extracted parameters being spectral information of each sub-band
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04M 2201/41 using speaker recognition speaker recognition per se G10L17/00
• CPC Class Codes: H04M 3/2236 Quality of speech transmission monitoring

Abstract

Methods and systems are provided for optimizing call quality and improving network efficiency by reducing bandwidth requirements at the individual-voice-call level. Embodiments provided herein build vocal fingerprints that correspond to the frequency range of the human voice, as well as the frequency range of the voice of individual users. The vocal fingerprints are used minimize and reduce the transmission of background noise and ambient sound captured using HD voice while retaining the frequency range of a user'"'"'s voice in HD voice. This filtered HD voice frequency range is then transmitted to recipients over the network. The reduced frequency range lowers bandwidth usage and conserves network resources, all while optimizing the call quality for individual users.

Claims

1. A method comprising:

via a server, generating a vocal fingerprint that is specific to a user, wherein the vocal fingerprint includes a frequency transmission range and a syllable emphasis pattern that uniquely correspond to a voice of the user as determined from a high-definition voice call that is associated with the user;

matching a frequency transmission range and a syllable emphasis pattern in a subsequent high-definition voice call to the vocal fingerprint that is specific to the user; and

determining that the frequency transmission range and the syllable emphasis pattern in the subsequent high-definition voice call matches the vocal fingerprint that is specific to the user and removing a portion of frequencies from the subsequent high-definition voice call when the portion of frequencies is outside of the frequency transmission range of the vocal fingerprint of the user.

2. The method of claim 1, further comprising determining that the frequency transmission range and the syllable emphasis pattern uniquely correspond to the voice of one user by monitoring at least one high-definition voice call that is associated with the one user.

3. The method of claim 2, wherein the at least one high-definition voice call is monitored in real-time with the occurrence of the at least one high-definition voice call.

4. The method of claim 2, further comprising monitoring two or more high-definition voice calls of the one user prior to generating the vocal fingerprint of the one user.

5. The method of claim 1, further comprising identifying the portion of frequencies of the subsequent high-definition voice call that outlie at least one of an upper buffer range or a lower buffer range of the frequency transmission range of the vocal fingerprint, wherein the portion of frequencies identified as outlying the at least one of the upper buffer range or the lower buffer range are removed from the subsequent high-definition voice call.

6. The method of claim 5, wherein the upper buffer range comprises 5 or more hertz above the highest frequency in the frequency transmission range of the vocal fingerprint.

7. The method of claim 5, wherein the lower buffer range comprises 5 or more hertz below the lowest frequency in the frequency transmission range of the vocal fingerprint.

8. The method of claim 1, wherein the frequency transmission range of the vocal fingerprint specifies a frequency range of 85 hertz to 180 hertz, 165 hertz to 255 hertz, or a combination thereof.

9. The method of claim 1, further comprising:

receiving an authorization to activate a voice call optimization feature;

based on the authorization, monitoring at least one high-definition voice call of the user prior to generating the vocal fingerprint of the user.

10. The method of claim 1, further comprising:

monitoring a plurality of high-definition voice calls of the user after generating the vocal fingerprint;

updating the vocal fingerprint based on the monitoring of the plurality of high-definition voice calls of the user, wherein updating the vocal fingerprint includes modifying at least one of the frequency transmission range or the syllable emphasis pattern that uniquely correspond to the voice of the user.

11. The method of claim 1, further comprising:

iteratively updating the vocal fingerprint by monitoring a plurality of high-definition voice calls of the user after generating the vocal fingerprint, wherein updating the vocal fingerprint includes modifying at least one of the frequency transmission range or the syllable emphasis pattern that uniquely correspond to the voice of the user.

12. The method of claim 1, wherein the subsequent high-definition voice call comprises a frequency range of 50 hertz to 7 kilohertz prior to optimization.

13. A system comprising:

a server, the server including;

a database storing a plurality of vocal fingerprints, each of the plurality of vocal fingerprints including a frequency transmission range and a syllable emphasis pattern that uniquely correspond to a voice of a user as determined by monitoring a first high-definition voice call that is associated with the user;

a monitoring module that intercepts a second high-definition voice call;

a referencing module that matches a frequency transmission range and a syllable emphasis pattern in the second high-definition voice call to one of the plurality of vocal fingerprints stored in the database, and that determines frequencies of the second high-definition voice call that outlie the frequency transmission range of the one of the plurality of vocal fingerprints matched to the second high-definition voice call; and

an optimization module that removes, from the second high-definition voice call, the frequencies of the second high-definition voice call that outlie the frequency transmission range of the one of the plurality of vocal fingerprints matched to the second high-definition voice call.

14. The system of claim 13, wherein the optimization module removes the frequencies of the second high-definition voice call that outlie the frequency transmission range of the one of the plurality of vocal fingerprints matched to the second high-definition voice call prior to transmitting remaining frequencies of the second high-definition voice call to a recipient.

15. The system of claim 13, wherein the second high-definition voice call is a frequency range that comprises 50 hertz to 7 kilohertz prior to optimization.

16. The system of claim 13, further comprising a librarian that periodically modifies one or more of the plurality of vocal fingerprints stored in the database based on subsequent high-definition voice calls.

17. The system of claim 16, wherein the librarian is configured to iteratively update one or more of the plurality of vocal fingerprints by monitoring the subsequent high-definition voice calls, wherein updating the vocal fingerprint includes modifying at least one of the frequency transmission range or the syllable emphasis pattern of the one or more of the plurality of vocal fingerprints.

18. One or more computer-readable storage media having computer-executable instructions embodied thereon are provided that, when executed, perform a method, the method comprising:

via a server, generating a vocal fingerprint that is specific to a user, wherein the vocal fingerprint includes a frequency range and a syllable emphasis pattern that uniquely correspond to a voice of the user as determined from a high-definition voice call that is associated with the user;

matching a frequency transmission range and a syllable emphasis pattern in a subsequent high-definition voice call to the vocal fingerprint that is specific to the user; and

when the frequency transmission range and the syllable emphasis pattern in the subsequent high-definition voice call match the vocal fingerprint of the user, removing a portion of frequencies from the subsequent high-definition voice call when the portion of frequencies is outside of the frequency transmission range of the vocal fingerprint of the user.