Method and apparatus for measuring quality of service in voice-over-IP network applications based on speech characteristics
View Patent ↗A method and apparatus for measuring Quality-of-Service (QoS) in packet-based communications networks for Voice-over-IP applications is advantageously based not only on packet loss information but also on particular characteristics of the speech data itself. Measurement of failures of the “quasi-stationary” (QS) property of speech—that is, the assumption that both the pitch and spectral envelop usually vary slowly relative to the packet size—are advantageously used in conjunction with measures of packet loss characteristics (e.g., packet loss rates or burst ratios) to calculate a QoS measure. One specific QS failure measure—referred to herein as QSFE (quasi-stationary failure estimate)—advantageously estimates the phoneme rate and is used in one illustrative method for calculating a QoS measure for Voice-over-IP applications in the presence of packet loss.
1. A method for calculating a Quality-of-Service measure in a packet-based communications network under packet loss conditions, the Quality-of-Service measure based on a sequence of packets transmitted over a period of time, the packets in said sequence comprising speech information, the method comprising the steps of:
receiving a plurality of said packets in said sequence;
determining a measure of packet loss based on said received packets; and
calculating the Quality-of-Service measure based on said measure of packet loss and on one or more characteristics of said speech information,
wherein said one or more characteristics of said speech information comprises a measure of a rate of failures of quasi-stationary speech behavior for said speech information comprised in said sequence of packets.
2. The method of claim 1 wherein said in measure of a rate of failures of quasi-stationary speech behavior comprises an estimate of a phoneme rate of said speech information comprised in said sequence of packets.
3. The method of claim 2 wherein said estimate of said phoneme rate of said speech information is calculated based on an energy distribution of a speech waveform represented by said speech information comprised in said sequence of packets and on one or more zero-crossings thereof.
4. The method of claim 1 wherein the Quality-of-Service measure is calculated as a product of said measure of packet loss and said measure of said rate of failures of quasi-stationary speech behavior.
5. The method of claim 1 wherein the Quality-of-Service measure is calculated as a summation of said measure of packet loss and said measure of said rate of failures of quasi-stationary speech behavior.
6. The method of claim 1 wherein said measure of packet loss comprises a packet loss rate.
7. The method of claim 1 wherein said measure of packet loss comprises a packet loss distortion rate.
8. The method of claim 1 wherein said measure of packet loss comprises a media distortion rate.
9. The method of claim 1 wherein said measure of packet loss comprises a burst ratio.
10. An apparatus for calculating a Quality-of-Service measure in a packet-based communications network under packet loss conditions, the Quality-of-Service measure based on a sequence of packets transmitted over a period of time, the packets in said sequence comprising speech information, the apparatus comprising a processor adapted to:
receive a plurality of said packets in said sequence;
determine a measure of packet loss based on said received packets; and
calculate the Quality-of-Service measure based on said measure of packet loss and on one or more characteristics of said speech information,
wherein said one or more characteristics of said speech information comprises a measure of a rate of failures of quasi-stationary speech behavior for said speech information comprised in said sequence of packets.
11. The apparatus of claim 10 wherein said measure of a rate of failures of quasi-stationary speech behavior comprises an estimate of a phoneme rate of said speech information comprised in said sequence of packets.
12. The apparatus of claim 11 wherein said estimate of said phoneme rate of said speech information is calculated based on an energy distribution of a speech waveform represented by said speech information comprised in said sequence of packets and on one or more zero-crossings thereof.
13. The apparatus of claim 10 wherein the Quality-of-Service measure is calculated as a product of said measure of packet loss and said measure of said rate of failures of quasi-stationary speech behavior.
14. The apparatus of claim 10 wherein the Quality-of-Service measure is calculated as a summation of said measure of packet loss and said measure of said rate of failures of quasi-stationary speech behavior.
15. The apparatus of claim 10 wherein said measure of packet loss comprises a packet loss rate.
16. The apparatus of claim 10 wherein said measure of packet loss comprises a packet loss distortion rate.
17. The apparatus of claim 10 wherein said measure of packet loss comprises a media distortion rate.
18. The apparatus of claim 10 wherein said measure of packet loss comprises a burst ratio.