Optimizing call quality using vocal frequency fingerprints to filter voice calls

• US 10,121,488 B1
• Filed: 02/23/2015
• Issued: 11/06/2018
• 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
• Application Number:
  US14/629,147
• Time in Patent Office: 1,352 Days
• Field of Search: 704226-227, 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 for improving call quality by filtering out frequencies outside of a specified frequency transmission range, the method comprising:

via a server;

monitoring one or more voice-call transmissions of an individual user;

analyzing data of the one or more voice-call transmissions monitored to identify frequency peaks and harmonics of the individual user'"'"'s voice;

generating a vocal fingerprint that is specific to the individual user from the analyzed data of the one or more voice-call transmissions monitored, wherein the vocal fingerprint includes a frequency transmission range, frequency peaks, and harmonics that uniquely correspond to the individual user'"'"'s voice;

storing the vocal fingerprint that is specific to the individual user on a server;

receiving another voice-call transmission of the individual;

matching frequency peaks and harmonics in the voice-call transmission received to the frequency peaks and harmonics of the vocal fingerprint that is specific to the individual user and stored on the server;

based on the matching vocal fingerprint that includes the frequency transmission range, frequency peaks, and harmonics that uniquely correspond to the individual user'"'"'s voice, removing data from the received voice-call transmission that outlies the frequency transmission range of the matching vocal fingerprint; and

communicating the remaining data of the voice-call transmission to a recipient of the voice-call transmission.

2. The method of claim 1, wherein the vocal fingerprint includes an individual user profile associated with a mobile device.

3. The method of claim 1, further comprising identifying an upper buffer range and a lower buffer range of the frequency transmission range of the vocal fingerprint.

4. The method of claim 1, further comprising identifying data of the received voice-call transmission corresponding to the frequency transmission range of the vocal fingerprint.

5. The method of claim 4, wherein the data of the received voice-call transmission identified as corresponding to the frequency transmission range of the vocal fingerprint includes one or more frequency ranges at or within the upper buffer range or the lower buffer range of the frequency transmission range of the vocal fingerprint.

6. 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.

7. The method of claim 1, wherein the voice-call transmission includes a frequency range corresponding to a high-definition (HD) voice frequency range.

8. A system for optimizing overall network call quality and reducing network bandwidth load, the system comprising:

a server communicatively coupled to a wireless network, wherein the server includes;

a voice-call-transmission monitoring module that;

monitors intercepted voice-call transmissions;

for each of the intercepted voice-call transmissions, identifies a frequency transmission range, frequency peaks, and harmonics that correspond to a voice in the intercepted voice-call transmissions; and

generates a plurality of vocal fingerprints, each of the plurality of vocal fingerprints corresponding to different individual users and that are usable to specifically identify the voices of the different individual users using the frequency transmission ranges, frequency peaks, and harmonics identified;

a vocal-fingerprint database storing the plurality of vocal fingerprints, each of the plurality of vocal fingerprints corresponding to different individual users, each of the plurality of vocal fingerprints including the frequency transmission range, the frequency peaks, and the harmonics of the voice of one individual user, wherein the frequency transmission range, the frequency peaks, and the harmonics of each of the plurality vocal fingerprints are usable to specifically identify the voice of the one individual user;

a vocal-fingerprint referencing module that references the vocal-fingerprint database to;

identify when the frequency transmission range, frequency peaks, and harmonics of one of the plurality of vocal fingerprints in the vocal-fingerprint database matches any additional intercepted voice-call transmissions; and

determine one or more frequency ranges of the additional intercepted voice-call transmissions that outlie the frequency transmission ranges of the one of the plurality of vocal fingerprints identified as corresponding to the additional intercepted voice-call transmissions; and

a voice-call-transmission optimization module that removes the one or more frequency ranges of the additional intercepted voice-call transmissions that outlie the one or more frequency transmission ranges of corresponding vocal fingerprints of the plurality of vocal fingerprints.

9. The system of claim 8, wherein the intercepted voice-call transmissions are high-definition (HD) voice transmissions.

10. The system of claim 8, wherein the voice-call-transmission optimization module removes the one or more frequency ranges of the additional intercepted voice-call transmissions that outlie the one or more frequency transmission ranges of the plurality of vocal fingerprints prior to transmitting a remaining frequency range of the additional intercepted voice-call transmissions to one or more recipients over the wireless network.

11. The system of claim 10, wherein the remaining frequency range corresponds to a frequency range within at least one vocal fingerprint of the plurality of vocal fingerprints.

12. The system of claim 10, wherein the remaining frequency range is less than an original frequency range of the additional intercepted voice-call transmissions before optimization.

13. The system of claim 10, wherein the additional intercepted voice-call transmissions includes a frequency range comprising 1 to 4000 hertz before optimization.

14. The system of claim 8, wherein the plurality of vocal fingerprints stored in the vocal-fingerprint database include one or more of an adult male vocal fingerprint, an adult female vocal fingerprint, an adolescent vocal fingerprint, a child vocal fingerprint, a regional vocal fingerprint, and a national vocal fingerprint.

15. The system of claim 8, further comprising a vocal-fingerprint librarian that modifies one or more of the plurality of vocal fingerprints stored in the vocal-fingerprint database based on frequency information received via the additional intercepted voice-call transmissions.

16. The system of claim 15, wherein the vocal-fingerprint librarian modifies the one or more of the plurality of vocal fingerprints stored in the vocal-fingerprint database periodically, continuously, or upon command.

17. The system of claim 8, wherein the vocal-fingerprint database further includes an upper buffer range and a lower buffer range for each 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 for maintaining and improving voice-call quality over a wireless network, the method comprising:

via a server;

monitoring one or more voice transmissions of an individual user;

analyzing data of the one or more voice transmission to identify frequency peaks and harmonics of the individual user'"'"'s voice;

generating a vocal fingerprint that is specific to the individual user, wherein the vocal fingerprint includes a frequency range, frequency peaks, and harmonics that uniquely correspond to the individual user'"'"'s voice;

storing the vocal fingerprint that is specific to the individual user on a server;

receiving another voice transmission of the individual user including a plurality of frequencies;

comparing the plurality of frequencies to the frequency range, the frequency peaks, and the harmonics of the stored vocal fingerprint that is specific to the individual user;

filtering outlying frequencies from the voice transmission based on the comparison to the stored vocal fingerprint, wherein outlying frequencies comprise frequencies in the voice transmission that outlie the frequency range of the stored vocal fingerprint; and

utilizing the outlying frequencies to optimize the voice transmission over the wireless network.