Source-based sound quality adjustment tool
Systems and methods for adjusting a sound level during a conference call are disclosed herein. Conferencing application receives an audio input including a first sound and a second sound. A user selectable element is generated for each sound in an user interface, where a user selection setting a first user selectable element associated with the first sound at a user-specified level is received. The sound level for the first sound is adjusted based on the user selection and output at the user-specified level while the second sound is output at a default sound level.
1. A method for adjusting a sound level during a conference call involving a plurality of devices via a communications network, the method comprising:
receiving an audio input at a first device of the plurality of devices;
determining, by control circuitry of the first device, that the audio input represents at least one of a first sound or a second sound, wherein the first sound is generated by a human speaker and the second sound is ambient input;
identifying a non-human source of the second sound that includes a portion of the ambient input;
analyzing the portion of the ambient input to generate a label;
generating for display a first user selectable element for a volume control of the human speaker, and generating for display a second user selectable element with the generated label for controlling the non-human source of the second sound including the portion of the ambient input, wherein the user selectable elements are adjustable within predetermined sound levels;
receiving a user selection setting a second user selectable element associated with the first sound at a first sound level different from a default sound level;
adjusting, by the control circuitry of the first device, a volume of the non-human source of the second sound including the portion of the ambient input; and
outputting the first sound at the first sound level while outputting the second sound including the portion of the ambient input at the default sound level and at the adjusted volume.
2. The method of claim 1 , wherein the adjusting the volume of the non-human source of the second sound including the portion of the ambient input comprises at least one of enhancing or reducing the second sound.
3. The method of claim 1 , wherein outputting the first sound at the first sound level is based on statistical spectral features including at least one of flatness, perceptual spread, or shape of the first sound.
4. The method of claim 1 , wherein the identifying the non-human source of the second sound that includes the portion of the ambient input includes using a source detection algorithm.
5. The method of claim 4 , wherein the source detection algorithm uses a learning model trained by a convolutional neural network.
6. The method of claim 5 , wherein the learning model is trained using combined audio data of the first and second sounds.
7. The method of claim 1 , further comprising:
generating for display a list of sources for the audio input on the user interface of the first device in real time.
8. The method of claim 1 , wherein each of the user selectable elements is a slider that moves along a sliding region of the respective one of the user selectable elements.
9. The method of claim 1 , further comprising:
identifying an additional non-human source of the second sound that includes an additional portion of the ambient input different from the portion of the ambient input;
analyzing the additional portion of the ambient input to generate an additional label; and
generating for display a third user selectable element with the additional generated label for controlling the additional non-human source of the second sound including the additional portion of the ambient input.
10. A system for adjusting a sound level during a conference call involving a plurality of devices via a communications network, the system comprising:
control circuitry configured to:
receive an audio input at a first device of the plurality of devices;
determine that the audio input represents at least one of a first sound or a second sound, wherein the first sound is generated by a human speaker and the second sound is ambient input;
identify a non-human source of the second sound that includes a portion of the ambient input;
analyze the portion of the ambient input to generate a label;
generate for display a first user selectable element for a volume control of the human speaker, and generating for display a second user selectable element with the generated label for controlling the non-human source of the second sound including the portion of the ambient input, wherein the user selectable elements are adjustable within predetermined sound levels;
receive a user selection setting a second user selectable element associated with the first sound at a first sound level different from a default sound level;
adjust by the control circuitry of the first device, a volume of the non-human source of the second sound including the portion of the ambient input; and
input/output circuitry configured to:
output the first sound at the first sound level while outputting the second sound including the portion of the ambient input at the default sound level and at the adjusted volume.
11. The system of claim 10 , wherein the adjusting the volume of the non-human source of the second sound including the portion of the ambient input comprises at least one of enhancing or reducing the second sound.
12. The system of claim 10 , wherein outputting the first sound at the first sound level is based on statistical spectral features including at least one of flatness, perceptual spread, or shape of the first sound.
13. The system of claim 10 , wherein the identifying the non-human source of the second sound that includes the portion of the ambient input includes using a source detection algorithm.
14. The system of claim 13 , wherein the source detection algorithm uses a learning model trained by a convolutional neural network.
15. The system of claim 14 , wherein the learning model is trained using combined audio data of the first and second sounds.
16. The system of claim 10 , wherein the control circuitry is further configured to:
generate for display a list of sources for the audio input on the user interface of the first device in real time.
17. The system of claim 10 , wherein each of the user selectable elements is a slider that moves along a sliding region of the respective one of the user selectable elements.
18. The system of claim 10 , wherein the control circuitry is further configured to:
identify an additional non-human source of the second sound that includes an additional portion of the ambient input different from the portion of the ambient input;
analyze the additional portion of the ambient input to generate an additional label; and
generate for display a third user selectable element with the additional generated label for controlling the additional non-human source of the second sound including the additional portion of the ambient input.