System and method for diagnostic modeling of audio and video quality of service
View Patent ↗Systems and methods are described for determining a set of three quality metrics for audio and/or video signals transmitted through a packet network. The set of three metrics provide more insight into which factors are affecting the quality of the received signal as perceived by the end-user. These three quality metrics measure reductions in quality due to lossy media transmission, packet loss concealment from packet loss and/or packet/frame jitter, and long periods of silence and/or frozen video. Because each metric quantifies a different aspect of transmitted quality, a deficiency in the transmitted signal can be identified by reference to the set.
1. A method for determining an objective quality model for quantifying quality of a received signal, the method comprising:
receiving at least one of a transmitted audio signal or a transmitted video signal;
determining a set of diagnostic quality metrics quantifying quality aspects of the received signal, comprising:
determining a first diagnostic quality metric for measuring a reduction in signal quality due to lossy media transmission;
determining a second diagnostic quality metric for measuring a reduction in signal quality due to packet loss concealment;
determining a third diagnostic quality metric for measuring a reduction in signal quality due to playout buffer underflow; and
wherein the first metric, the second metric, and the third metric are all different and are all provided in the set.
2. The method of claim 1 , further comprising:
responsive to receiving both an audio signal and a video signal:
separating the received audio signal from the received video signal;
determining a first set of diagnostic quality metrics for the received audio signal; and
determining a second set of diagnostic quality metrics for the received video signal.
3. The method of claim 1 , wherein the first diagnostic quality metric is inversely proportional to a first ratio of a mean bit-rate of the received signal divided by a maximum bit-rate of a codec decoding the received signal, and is inversely proportional to a second ratio of a mean frame rate of the received signal divided by a maximum frame rate of the codec decoding the received signal.
4. The method of claim 1 , wherein the first quality metric is normalized for a bandwidth of the received signal.
5. The method of claim 1 , wherein the second diagnostic quality metric is directly proportional to a proportion of frames classified as bad and a proportion of frames classified as damaged.
6. The method of claim 1 , wherein the third diagnostic quality metric is directly proportional to a sum of a number of freeze events.
7. The method of claim 6 , wherein each freeze event of the sum is weighted by a factor proportional to a duration corresponding to each freeze event.
8. The method of claim 1 , wherein the third diagnostic quality metric is directly proportional to a distribution of freeze event duration.
9. The method of claim 1 , wherein at least one diagnostic quality metric of the set is a null value.
10. The method of claim 1 , wherein the transmitted audio signal, the transmitted video signal, or both, are transmitted using a conversational transmission application.
11. The method of claim 1 , wherein the transmitted audio signal, the transmitted video signal, or both, are transmitted using a streaming application.
12. A system for determining an objective quality model for quantifying quality of a received signal, the system comprising:
a packet capture device configured to receive network packets transmitted as a media stream through a packet network;
a receiver model configured to identify the media stream and classify the network packets of the stream as good, bad, or damaged;
a quality determination unit configured for execution of computer program code for determining a set of diagnostic quality metrics, comprising:
determining a first diagnostic quality metric for measuring a reduction in signal quality due to lossy media transmission;
determining a second diagnostic quality metric for measuring a reduction in signal quality due to packet loss concealment;
determining a third diagnostic quality metric for measuring a reduction in signal quality due to playout buffer underflow; and
wherein the first metric, the second metric, and the third metric are all different and are all provided in the set.
13. The method of claim 12 , further comprising:
responsive to receiving both an audio signal and a video signal:
separating the received audio signal from the received video signal;
determining a first set of diagnostic quality metrics for the received audio signal; and
determining a second set of diagnostic quality metrics for the received video signal.
14. The method of claim 12 , wherein the first diagnostic quality metric is inversely proportional to a first ratio of a mean bit-rate of the received signal divided by a maximum bit-rate of a codec decoding the received signal, and is inversely proportional to a second ratio of a mean frame rate of the received signal divided by a maximum frame rate of the codec decoding the received signal.
15. The method of claim 12 , wherein the first quality metric is normalized for a bandwidth of the received signal.
16. The method of claim 12 , wherein the second diagnostic quality metric is directly proportional to a proportion of frames classified as bad and a proportion of frames classified as damaged.
17. The method of claim 12 , wherein the third diagnostic quality metric is directly proportional to a sum of a number of freeze events.
18. The method of claim 17 , wherein each freeze event of the sum is weighted by a factor proportional to a duration corresponding to each freeze event.
19. The method of claim 12 , wherein the third diagnostic quality metric is directly proportional to a distribution of freeze event duration.
20. The method of claim 12 , wherein at least one diagnostic quality metric of the set is a null value.
21. The method of claim 12 , wherein at least one of a transmitted audio signal or a transmitted video signal are transmitted using a conversational transmission application.
22. The method of claim 12 , wherein at least one of a transmitted audio signal or a transmitted video signal are transmitted using a streaming application.