Identifying the network segment responsible for poor audio quality

A computer system comprising:

• a processor;
• a memory device coupled to the processor;
• and
• a computer readable storage device coupled to the processor, wherein the storage device contains program code executable by the processor via the memory device to implement a method comprising:
• identifying, by a processor of a computing system, a plurality of parameters associated with a telephone call;
• calculating, by the processor, a probability that a particular network segment is responsible for poor audio quality associated with the telephone call based on the plurality of parameters;
• biasing, by the processor, the probability:
• for a first category of calls to indicate that a calling party's access network downlink is most likely to have introduced the poor audio, wherein the processor infers that a human calling party disconnected the call due to the human calling party's detection of poor audio quality, such that the only network segment involved is the calling party's access network downlink serving the calling party;
• for a second category of calls to indicate that the called party's access network uplink is most likely to have introduced the poor audio quality, wherein the processor infers that the call is abandoned because the calling party perceives that the audio greeting from the called party has been impaired en-route, and the called party's access network uplink is responsible because the called party's access network uplink is the network segment that has been added upon a call answer and transmitting the called party's greeting;
• and
• classifying, by the processor, a call according to which network segment is responsible for the poor audio quality associated with the telephone call.

A computer program product, comprising a computer readable hardware storage device storing a computer readable program code, the computer readable program code comprising an algorithm that when executed by a computer processor of a computing system implements a method comprising:

• identifying, by a processor of a computing system, a plurality of parameters associated with a telephone call;
• calculating, by the processor, a probability that a particular network segment is responsible for poor audio quality associated with the telephone call based on the plurality of parameters;
• biasing, by the processor, the probability:
• for a first category of calls to indicate that a calling party's access network downlink is most likely to have introduced the poor audio, wherein the processor infers that a human calling party disconnected the call due to the human calling party's detection of poor audio quality, such that the only network segment involved is the calling party's access network downlink serving the calling party;
• for a second category of calls to indicate that the called party's access network uplink is most likely to have introduced the poor audio quality, wherein the processor infers that the call is abandoned because the calling party perceives that the audio greeting from the called party has been impaired en-route, and the called party's access network uplink is responsible because the called party's access network uplink is the network segment that has been added upon a call answer and transmitting the called party's greeting;
• and
• classifying, by the processor, a call according to which network segment is responsible for the poor audio quality associated with the telephone call.