Audio fingerprint differences for end-to-end quality of experience measurement

1. A method to determine mobile Quality of Experience, comprising:

generating, by a first device, a first audio fingerprint from a digital audio signal; and

transmitting, by the first device, the digital audio signal and the first audio fingerprint to a second device via a network;

the second device being configured to:

generate a second audio fingerprint from the digital audio signal received from the first device,

compare the first audio fingerprint and the second audio fingerprint generated from the digital audio signal, and

determine a Quality of Experience (QoE) metric value based at least in part on the comparison, wherein a difference between the first audio fingerprint and the second audio fingerprint based on the comparison provides QoE metric value of characteristics including transmission medium quality or coding effects in mobile communications system.

2. The method of claim 1 , wherein the digital audio signal comprises a Voice over IP (VoIP) signal.

3. The method of claim 1 , wherein the second device is further configured to determine the QoE metric value based at least in part on a comparison between a third audio fingerprint and at least one of the first audio fingerprint and the second audio fingerprint, and wherein the third audio fingerprint is generated at the second device in response, at least in part, to audio captured by at least one microphone located at the second device.

4. The method of claim 3 , wherein the first device comprises a first cellular telephone handset, and wherein the second device comprises a second cellular telephone handset.

5. The method of claim 1 , wherein the first device comprises a first network node, and wherein the second device comprises a second network node.

6. The method of claim 5 , wherein at least one of the first network node and/or the second network node comprises a server.

7. The method of claim 1 , wherein the first audio fingerprint and the second audio fingerprint are generated during and/or after a communication event.

8. The method of claim 1 , wherein the first device is configured to transmit the first audio fingerprint and the digital audio signal simultaneously or separately.

9. The method of claim 1 , wherein the second audio fingerprint is generated before a conversion of the received digital audio signal to an analog signal.

10. The method of claim 1 , wherein the second device is further configured to dynamically compare in nearly real-time the first audio fingerprint and the second audio fingerprint generated from the digital audio signal.

11. The method of claim 1 , wherein the second device is further configured to compare the first audio fingerprint and the second audio fingerprint generated from the digital audio signal based on data capability of the second device, and wherein packet timing and identification is used to facilitate synchronization between the first audio fingerprint and the second audio fingerprint.

12. The method of claim 1 , wherein the first device is configured to preprocess the digital audio signal by:

converting the digital audio signal into a standard format using a 16 bit Pulse-code Modulation (PCM) format or band-pass filtering; and

transforming the digital audio signal using a Fast Fourier Transform (FFT), a Discrete Fourier Transform (DFT), a Haar Transform, or a Walsh-Hadmard transform.

13. The method of claim 1 , wherein the second device is further configured to compare between perceptual characteristics of the first audio fingerprint and perceptual characteristics of the second audio fingerprint.

14. The method of claim 13 , wherein the perceptual characteristics comprises at least one of average zero crossing rate, estimated tempo, average spectrum, spectral flatness, prominent tones across one or more spectral bands, or bandwidth, and wherein a feature corresponding to the spectral flatness is obtained by estimating a tone-like or noise-like quality for a band in a frame's signal spectrum and a feature corresponding to the prominent tones across one or more spectral bands includes an ordered list of band indices having prominent tones in a frame.

15. The method of claim 1 , wherein the first audio fingerprint and the second audio fingerprint include one or more features arranged in one or more feature vectors and the vectors are binary encoded, and wherein the first audio fingerprint and the second audio fingerprint are provided in compact form by clustering feature vectors into sequences and then approximating the feature vectors with representative code vectors associated with a codebook.

16. The method of claim 1 , wherein the first audio fingerprint and the second audio fingerprint include one or more feature vectors and the second device is further configured to compare the first audio fingerprint and the second audio fingerprint by determining a distance metric between fingerprint feature vectors, and wherein the distance metric provides a measure of the similarity of various feature vectors being compared; and

wherein the second device is further configured to compare the distance metric to a threshold value, assign a failed value to a corresponding QoE metric when the distance meets or exceeds a threshold value, and assign a pass value to a corresponding QoE metric when the distance falls below the threshold value.

17. A method to determine mobile Quality of Experience by a first device, comprising:

receiving a first audio fingerprint generated from a digital audio signal via a network, the first audio fingerprint being generated at a second device which is a transmission source of the digital audio signal;

generating a second audio fingerprint from the digital audio signal received from the second device;

comparing the first audio fingerprint and the second audio fingerprint generated from the digital audio signal; and

determining a Quality of Experience (QoE) metric value based at least in part on the comparison, wherein a difference between the first audio fingerprint and the second audio fingerprint based on the comparison provides QoE metric value of characteristics including transmission medium quality or coding effects in mobile communications system.

18. The method of claim 17 , wherein the determining the QoE metric value comprises determining the QoE metric value based at least in part on a comparison between a third audio fingerprint and at least one of the first audio fingerprint and the second audio fingerprint, and wherein the third audio fingerprint is generated at the first device in response, at least in part, to audio captured by at least one microphone located at the first device.

19. The method of claim 18 , wherein the first device comprises a first cellular telephone handset, and wherein the second device comprises a second cellular telephone handset.

20. The method of claim 17 , wherein the first device comprises a first network node, and wherein the second device comprises a second network node.

21. A system comprising:

a first device configured to:

generate a first audio fingerprint from a digital audio signal, and

transmit the digital audio signal and the first audio fingerprint to a second device via a network; and

a second device configured to:

generate a second audio fingerprint from the digital audio signal received from the first device,

compare the first audio fingerprint and the second audio fingerprint generated from the digital audio signal, and

determine a Quality of Experience (QoE) metric value based at least in part on the comparison, wherein a difference between the first audio fingerprint and the second audio fingerprint based on the comparison provides QoE metric value of characteristics including transmission medium quality or coding effects in mobile communications system.