Quality-of-experience measurement for voice services

• US 9,407,680 B2
• Filed: 09/25/2015
• Issued: 08/02/2016
• Est. Priority Date: 02/10/2011
• Status: Expired due to Fees

• Current Assignee: Empire Technology Development LLC (Allied Inventors Management, LLC)
• Original Assignee: Empire Technology Development LLC (Allied Inventors Management, LLC)
• Inventors: Cao, Junwei, Qian, Han, Li, Junwei
• Primary Examiner(s): Liu, Siming
• Application Number:
  US14/864,920
• Publication Number:
  US 20160014187A1
• Time in Patent Office: 312 Days
• US Class Current: 1/1
• CPC Class Codes: G10L 2025/906 Pitch tracking
• CPC Class Codes: G10L 25/09 the extracted parameters being zero crossing rates
• CPC Class Codes: G10L 25/60 for measuring the quality of voice signals
• CPC Class Codes: G10L 25/63 for estimating an emotional state
• CPC Class Codes: G10L 25/90 Pitch determination of speech signals
• CPC Class Codes: H04L 41/5067 Customer-centric QoS measurements
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04L 65/1083 In-session procedures
• CPC Class Codes: H04L 65/80 Responding to QoS

Abstract

An example method to determine a quality-of-experience (QoE) metric for a network communication includes receiving a media signal from the network communication, wherein the media signal includes a voice component, extracting an experience indicator from the voice component, wherein the experience indicator is a voice feature descriptive of a service quality of the network communication, evaluating the experience indicator, retrieving a quality-of-service (QoS) metric if the evaluated experience indicator reflects the service quality of the network possibly being subpar, and determining the QoE metric for the network communication based on the evaluated experience indicator and the retrieved QoS metric for the network communication.

Claims

1. A method to determine a quality-of-experience (QoE) metric for a network communication, comprising:

receiving a media signal from the network communication, wherein the media signal includes a voice component;

extracting an experience indicator from the voice component, wherein the experience indicator is a voice feature descriptive of a service quality of the network communication;

evaluating the experience indicator;

retrieving a quality-of-service (QoS) metric if the evaluated experience indicator reflects the service quality of the network possibly being subpar; and

determining the QoE metric for the network communication based on the evaluated experience indicator and the retrieved QoS metric for the network communication.

2. The method as recited in claim 1, wherein the voice feature is an emotion-change amplitude measurement.

3. The method as recited in claim 1, wherein the voice feature is a voice-pacing time measurement.

4. The method as recited in claim 1, wherein the voice feature is a sound-volume pitch measurement.

5. The method as recited in claim 1, wherein the voice feature is a corpus.

6. The method as recited in claim 1, further comprising detecting the voice component in the media signal based on zero-crossing rate.

7. The method as recited in claim 1, further comprising recording a start time and an end time for the voice component.

8. The method as recited in claim 1, wherein the determining the QoE metric is performed if the QoS metric the service quality of the network possibly being subpar.

9. A method to determine quality of a network communication, comprising:

receiving a media signal from the network communication;

extracting a first corpus from the media signal, wherein the extraction of the first corpus comprises;

reducing noise from the received media signal,

extracting a plurality of voice segments from the media signal,

recognizing a plurality of words from the plurality of voice segments, and

identifying the first corpus based on the plurality of words;

extracting an experience indicator based on evaluating the first corpus;

retrieving a quality-of-service (QoS) metric if the experience indicator reflects the service quality of the network possibly being subpar; and

determining a first QoE metric for the network communication based on the evaluated first corpus and the retrieved QoS metric for the network communication.

10. The method as recited in claim 9, wherein the determining of the first QoE metric further comprising:

retrieving a second QoE metric for a second corpus, wherein the first corpus is subsequent to the second corpus in the media signal; and

initializing the first QoE metric based on the second QoE metric, the first corpus, and the QoS metric for the network communication.

11. The method as recited in claim 9, wherein the determining of the first QoE metric further comprising:

retrieving a second QoE metric for a second corpus, wherein the first corpus is subsequent to the second corpus in the media signal; and

exponentially increasing the first QoE metric based on the second QoE metric, the first corpus, and the QoS metric for the network communication.

12. The method as recited in claim 9, wherein the service quality indicated by the first corpus has a delay condition, a decay condition, or a jitter condition.

13. A system configured to determine a quality-of-experience (QoE) metric for a network communication, comprising:

a processor; and

a memory encoded with executable instructions, which in response to execution by the processor, causes the processor to

receive a media signal from the network communication, wherein the media signal includes a voice component,

extract an experience indicator from the voice component, wherein the experience indicator is a voice feature descriptive of a service quality of the network communication,

evaluate the experience indicator,

retrieve a quality-of-service (QoS) metric if the evaluated experience indicator reflects the service quality of the network possibly being subpar, and

determine the QoE metric for the network communication based on the evaluated experience indicator and the retrieved QoS metric for the network communication.

14. The system as recited in claim 13, wherein the memory is encoded with additional instructions for detecting the voice component in the media signal based on zero-crossing rate.

15. The system as recited in claim 13, wherein the memory is encoded with additional instructions for recording a start time and an end time for the voice segment.

16. The system as recited in claim 13, wherein the memory is encoded with additional instructions for determining the QoE metric if the QoS metric the service quality of the network possibly being subpar.

17. A system configured to determine quality of a network communication, comprising:

a processor; and

a memory encoded with executable instructions, which in response to execution by the processor, causes the processor to

receive a media signal from the network communication;

extract a first corpus from the media signal, wherein the extraction of the first corpus includes

reducing noise from the received media signal,

extracting a plurality of voice segments from the media signal,

recognizing a plurality of words from the plurality of voice segments, and

identifying the first corpus based on the plurality of words;

extract an experience indicator based on evaluating the first corpus,

retrieve a quality-of-service (QoS) metric if the experience indicator reflects the service quality of the network possibly being subpar; and

determine a first QoE metric for the network communication based on the evaluated first corpus and the retrieved QoS metric for the network communication.

18. The system as recited in claim 17, wherein the instructions for determining the first QoE metric, in response to execution by the processor, cause the processor to further:

retrieve a second QoE metric for a second corpus, wherein the first corpus is subsequent to the second corpus in the media signal; and

initialize the first QoE metric based on the second QoE metric, the first corpus, and the QoS metric for the network communication.

19. The system as recited in claim 17, wherein the instructions for determining the first QoE metric, in response to execution by the processor, cause the processor to further:

retrieve a second QoE metric for a second corpus, wherein the first corpus is subsequent to the second corpus in the media signal; and

exponentially increase the first QoE metric based on the second QoE metric, the first corpus, and the QoS metric for the network communication.

20. The system as recited in claim 17, wherein the service quality indicated by the first corpus has a delay condition, a decay condition, or a jitter condition.