Audio conference platform with dynamic speech detection threshold
View Patent ↗The present invention comprises a method for audio/video conferencing. In a preferred embodiment, the method comprises using a dynamic threshold value to determine whether there is speech on a line. One aspect, the method comprises determining a dynamic threshold value based on one or more characteristics of signals received on a port, associating that dynamic threshold value with the port; and comparing one or more characteristics of signals subsequently received on the port to the dynamic threshold value. Signals received over a plurality of ports are summed, but for ports whose signal characteristics have a specified relationship to the dynamic threshold value associated with that port, signals are not contained in the sum.
1. A method for conferencing, comprising:
receiving a plurality of audio signals over a plurality of ports of a conferencing system;
determining whether valid speech is present in a first audio signal received over at least one port;
defaulting to a DTMF status of negative for the at least one port;
setting the DTMF status to positive if a DTMF tone is received from the at least one port;
if valid speech is present and DTMF status is negative, including the first audio signal in a conference sum audio signal provided to at least some participants of the conference; and
if valid speech is not present or if DTMF status is positive, omitting the first audio signal from a conference sum audio signal provided to at least some participants of the conference.
2. The method of claim 1 , wherein determining whether valid speech is present comprises:
determining whether noise is present in the first audio signal;
determining a dynamic threshold value for the at least one port if it was determined that noise was present; and
comparing a characteristic of the first audio signal to the determined dynamic threshold value.
3. The method of claim 2 , wherein the characteristic comprises audio signal energy.
4. The method of claim 2 , wherein the characteristic comprises audio signal magnitude.
5. The method of claim 2 , wherein the first audio signal is included in the conference sum only if the characteristic exceeds the dynamic threshold value.
6. The method of claim 2 , wherein determining whether noise is present in the first audio signal comprises a comparison to a noise threshold.
7. The method of claim 1 , further comprising:
determining a DTMF status of negative if a DTMF tone is received from the at least one port while the DTMF status of the at least one port is positive.
8. A non-transitory computer readable medium having computer code stored thereon to perform a method for conferencing, the computer code comprising computer instructions to cause a computer processor to:
receive a plurality of audio signals over a plurality of ports of a conferencing system;
determine whether valid speech is present in a first audio signal received over at least one port;
default to a DTMF status of negative for the at least one port;
set the DTMF status to positive if a DTMF tone is received from the at least one port;
if valid speech is present and DTMF status is negative, include the first audio signal in a conference sum audio signal provided to at least some participants of the conference; and
if valid speech is not present or if DTMF status is positive, omit the first audio signal from a conference sum audio signal provided to at least some participants of the conference.
9. The non-transitory computer readable medium of claim 8 , wherein the computer instructions to determine whether valid speech is present comprise computer instructions to cause the computer processor to:
determine whether noise is present in the first audio signal;
determine a dynamic threshold value for the at least one port if it was determined that noise was present; and
compare a characteristic of the first audio signal to the determined dynamic threshold value.
10. The non-transitory computer readable medium of claim 9 , wherein the characteristic comprises audio signal energy.
11. The non-transitory computer readable medium of claim 9 , wherein the characteristic comprises audio signal magnitude.
12. The non-transitory computer readable medium of claim 9 , wherein the first audio signal is included in the conference sum only if the characteristic exceeds the dynamic threshold value.
13. The non-transitory computer readable medium of claim 9 , wherein the computer instructions to determine whether noise is present in the first audio signal comprise computer instructions to perform a comparison to a noise threshold.
14. The non-transitory computer readable medium of claim 8 , wherein the computer instructions further comprise computer instructions to cause the computer processor to:
determine a DTMF status of negative if a DTMF tone is received from the at least one port while the DTMF status of the at least one port is positive.
15. A conferencing device to manage an audio portion of a conference, the conferencing device comprising a programmable processor configured with computer code to perform a method for conferencing, the computer code comprising computer instructions to cause the conferencing device to:
receive a plurality of audio signals over a plurality of ports of a conferencing system;
determine whether valid speech is present in a first audio signal received over at least one port;
default to a DTMF status of negative for the at least one port;
set the DTMF status to positive if a DTMF tone is received from the at least one port;
if valid speech is present and DTMF status is negative, include the first audio signal in a conference sum audio signal provided to at least some participants of the conference; and
if valid speech is not present or if DTMF status is positive, omit the first audio signal from a conference sum audio signal provided to at least some participants of the conference.
16. The conferencing device of claim 15 , wherein the computer instructions to determine whether valid speech is present comprise computer instructions to cause the conferencing device to:
determine whether noise is present in the first audio signal;
determine a dynamic threshold value for the at least one port if it was determined that noise was present; and
compare a characteristic of the first audio signal to the determined dynamic threshold value.
17. The conferencing device of claim 16 , wherein the characteristic comprises audio signal energy.
18. The conferencing device of claim 16 , wherein the characteristic comprises audio signal magnitude.
19. The conferencing device of claim 16 , wherein the first audio signal is included in the conference sum only if the characteristic exceeds the dynamic threshold value.
20. The conferencing device of claim 16 , wherein the computer instructions to determine whether noise is present in the first audio signal comprise computer instructions to perform a comparison to a noise threshold.
21. The conferencing device of claim 15 , wherein the computer instructions further comprise computer instructions to cause the conferencing device to:
determine a DTMF status of negative if a DTMF tone is received from the at least one port while the DTMF status of the at least one port is positive.