Method and apparatus for quantifying, predicting and monitoring the conversational quality

1. A method of quantifying a voice quality in a telecommunication system including a first gateway in communication with a second gateway over a packet network, the method comprising:

embedding a probe signal in a first speech signal from a first talker to generate a third speech signal, the first speech signal having a voice portion and a silence portion, wherein embedding includes masking the probe signal by the voice portion of the first speech signal;

transmitting the third speech signal to the second gateway over the packet network;

receiving a modified third speech signal over the packet network from the second gateway; and

deriving speech parameters from a first speech signal of the first talker received by the first gateway over a first communication line and the modified third speech signal received by the first gateway from the second gateway over the packet network;

determining a conversational impairment index using the speech parameters;

deriving technology parameters based on voice technology and components in the telecommunication system;

determining a technology impairment index using the technology parameters; and

mapping the conversational impairment index and the technology impairment index into a conversational quality index to quantify the voice quality in the telecommunication system.

2. The method of claim 1 , wherein the determining the conversational impairment index applies weighting to the speech parameters.

3. The method of claim 1 , wherein the determining the technology impairment index applies weighting to the technology parameters.

4. The method of claim 1 , wherein the speech parameters include one or more of the following parameters: a double-talk ratio (DTR), a number of false starts during double-talk (FSDT), a number of false starts during single-talk (FSST), a mutual silence (MS), a mutual silence ratio (MSR) and a ratio of the first talker speech to the second talker background noise (RTS_LTN_SNR).

5. The method of claim 1 , wherein the speech parameters include the following parameters: a double-talk ratio (DTR), a number of false starts during double-talk (FSDT), a number of false starts during single-talk (FSST), a mutual silence (MS), a mutual silence ratio (MSR) and a ratio of the first talker speech to the second talker background noise (RTS_LTN_SNR).

6. The method of claim 1 , wherein the technology parameters include one or more of the following parameters: A round trip delay (RTD), an echo return loss enhancement (ERLE), a speech codec type (SCT), a network packet jitter (NPJ), a packet loss and packet loss concealment (PL/PLC), a tandem free operation (TFO), a transcoding free operation (TrFO), a voice activity detector usage (VADU), an adaptive noise reduction usage (ANRU) and a network transmission loss plan (NTLP).

7. The method of claim 1 , wherein the technology parameters include the following parameters: A round trip delay (RTD), an echo return loss enhancement (ERLE), a speech codec type (SCT), a network packet jitter (NPJ), a packet loss and packet loss concealment (PL/PLC), a tandem free operation (TFO), a transcoding free operation (TrFO), a voice activity detector usage (VADU), an adaptive noise reduction usage (ANRU) and a network transmission loss plan (NTLP).

8. A computer readable media including a software program residing in a gateway and for execution by a controller of the gateway for quantifying a voice quality in a telecommunication system including the first gateway in communication with a second gateway over a packet network, the software program comprising:

code for embedding a probe signal in a first speech signal from a first talker to generate a third speech signal, the first speech signal having a voice portion and a silence portion, wherein embedding includes masking the probe signal by the voice portion of the first speech signal;

code for transmitting the third speech signal to the second gateway over the packet network;

code for receiving a modified third speech signal over the packet network from the second gateway; and

code for deriving speech parameters from a first speech signal of the first talker received by the first gateway over a first communication line and the modified third speech signal received by the first gateway from the second gateway over the packet network;

code for determining a conversational impairment index using the speech parameters;

code for deriving technology parameters based on voice technology and components in the telecommunication system;

code for determining a technology impairment index using the technology parameters; and

code for mapping the conversational impairment index and the technology impairment index into a conversational quality index to quantify the voice quality in the telecommunication system.

9. The computer readable media of claim 8 , wherein the code for determining the conversational impairment index applies weighting to the speech parameters.

10. The computer readable media of claim 8 , wherein the code for determining the technology impairment index applies weighting to the technology parameters.

11. The computer readable media of claim 8 , wherein the speech parameters include one or more of the following parameters: a double-talk ratio (DTR), a number of false starts during double-talk (FSDT), a number of false starts during single-talk (FSST), a mutual silence (MS), a mutual silence ratio (MSR) and a ratio of the first talker speech to the second talker background noise (RTS_LTN_SNR).

12. The computer readable media of claim 8 , wherein the technology parameters include one or more of the following parameters: A round trip delay (RTD), an echo return loss enhancement (ERLE), a speech codec type (SCT), a network packet jitter (NPJ), a packet loss and packet loss concealment (PL/PLC), a tandem free operation (TFO), a transcoding free operation (TrFO), a voice activity detector usage (VADU), an adaptive noise reduction usage (ANRU) and a network transmission loss plan (NTLP).

13. A first gateway for quantifying a voice quality in a telecommunication system including the first gateway in communication with a second gateway over a packet network, the first gateway comprising:

a controller configured to:

embed a probe signal in a first speech signal from a first talker to generate a third speech signal, the first speech signal having a voice portion and a silence portion, wherein embedding includes masking the probe signal by the voice portion of the first speech signal;

transmit the third speech signal to the second gateway over the packet network;

receive a modified third speech signal over the packet network from the second gateway;

derive speech parameters from a first speech signal of the first talker received by the first gateway over a first communication line and the modified third speech signal received by the first gateway from the second gateway over the packet network;

a voice quality monitoring module configured to determine a conversational impairment index using the speech parameters;

the voice quality monitoring module further configured to derive technology parameters based on voice technology and components in the telecommunication system;

the voice quality monitoring module further configured to determine a technology impairment index using the technology parameters; and

the voice quality monitoring module further configured to map the conversational impairment index and the technology impairment index into a conversational quality index to quantify the voice quality in the telecommunication system.

14. The first gateway of claim 13 , wherein the voice quality monitoring module is further configured to apply weighting to the speech parameters for determining the conversational impairment index.

15. The first gateway of claim 13 , wherein the voice quality monitoring module is further configured to apply weighting to the technology parameters for determining the technology impairment index.

16. The first gateway of claim 13 , wherein the speech parameters include one or more of the following parameters: a double-talk ratio (DTR), a number of false starts during double-talk (FSDT), a number of false starts during single-talk (FSST), a mutual silence (MS), a mutual silence ratio (MSR) and a ratio of the first talker speech to the second talker background noise (RTS_LTN_SNR).