Modulation-based call exit management
In aspects of modulation-based call exit management, a media device detects that a user desires to exit a conference call and determines whether a video feed of the conference call is active or inactive. Based on the video feed being active, the media device applies at least one of modulation or a depth effect to the pre-recorded audio message to generate a modified pre-recorded audio message. Based on the video feed being inactive, the media device records an audio message of the user reading the contextual transcript during the conference call to generate a recorded audio message and applies at least one of the modulation or the depth effect to the recorded audio message to generate a modified recorded audio message. The media device provides the modified pre-recorded audio message or the modified recorded audio message to a speaker that emits the provided audio message.
1 . A method, comprising:
maintaining a contextual transcript and a pre-recorded audio message;
detecting that a user desires to exit a conference call;
determining that a video feed of the conference call is active or inactive, and one of:
based on the video feed of the conference call being active;
displaying a prompt to generate a modified pre-recorded audio message;
generating the modified pre-recorded audio message by applying at least one of modulation or a depth effect to the pre-recorded audio message to sound like someone other than the user; and
providing the modified pre-recorded audio message to an external speaker that emits the modified pre-recorded audio message; or
based on the video feed of the conference call being inactive:
recording an audio message of the user reading the contextual transcript during the conference call to generate a recorded audio message;
applying at least one of the modulation or the depth effect to the recorded audio message to generate a modified recorded audio message; and
providing the modified recorded audio message to the external speaker that emits the modified recorded audio message.
2 . The method of claim 1 , wherein the detecting includes detecting a gesture of the user that indicates the user desires to exit the conference call.
3 . The method of claim 1 , wherein the detecting includes detecting a comment communicated by the user during the conference call that indicates the user desires to exit the conference call.
4 . The method of claim 1 , wherein the video feed being active includes a camera of a computing device capturing video images of the user.
5 . The method of claim 1 , wherein generating the modified pre-recorded audio message includes selecting the pre-recorded audio message and at least one of the modulation or the depth effect applied to the pre-recorded audio message.
6 . The method of claim 5 , wherein the pre-recorded audio message is a recording of the user reading the contextual transcript before the conference call.
7 . The method of claim 1 , further comprising:
displaying the prompt on a media device instructing the user to look in an indicated direction.
8 . A system, comprising:
a memory to maintain a contextual transcript and a pre-recorded audio message; and
a processor coupled with the memory, the processor configured to cause the system to:
detect that a user desires to exit a conference call;
determine that a video feed of the conference call is active or inactive, and one of:
based on the video feed of the conference call being active:
apply at least one of modulation or a depth effect to the pre-recorded audio message to generate a modified pre-recorded audio message; and
provide the modified pre-recorded audio message to an external speaker that emits the modified pre-recorded audio message; or
based on the video feed of the conference call being inactive:
display a prompt to generate a recorded audio message;
generate the recorded audio message by recording an audio message of the user reading the contextual transcript during the conference call;
apply at least one of the modulation or the depth effect to the recorded audio message to generate a modified recorded audio message that sounds like someone other than the user; and
provide the modified recorded audio message to the external speaker that emits the modified recorded audio message.
9 . The method system of claim 8 , wherein the system is configured to detect a gesture of the user that indicates the user desires to exit the conference call.
10 . The system of claim 8 , wherein the system is configured to detect a comment communicated by the user during the conference call that indicates the user desires to exit the conference call.
11 . The system of claim 8 , wherein the system is configured to display the contextual transcript on a screen.
12 . The system of claim 11 , wherein the system is configured to:
mute the conference call; and
record the audio message of the user while the conference call is muted.
13 . A media device, comprising:
a memory to maintain a contextual transcript and a pre-recorded audio message; and
a processor coupled with the memory, the processor configured to cause the media device to:
detect that a user desires to exit a conference call;
determine whether a video feed of the conference call is active or inactive, and one of:
based on the video feed being active:
apply at least one of modulation or a depth effect to the pre-recorded audio message to generate a modified pre-recorded audio message; and
provide the modified pre-recorded audio message to a speaker that emits the modified pre-recorded audio message; or
based on the video feed being inactive:
record an audio message of the user reading the contextual transcript during the conference call to generate a recorded audio message;
apply at least one of the modulation or the depth effect to the recorded audio message to generate a modified recorded audio message; and
provide the modified recorded audio message to the speaker that emits the modified recorded audio message.
14 . The media device of claim 13 , wherein the processor further causes the media device to detect a gesture of the user that indicates the user desires to exit the conference call.
15 . The media device of claim 13 , wherein the processor further causes the media device to detect a comment communicated by the user during the conference call that indicates the user desires to exit the conference call.
16 . The media device of claim 13 , based on the video feed being active, the processor further causes the media device to display a prompt on at least one of the media device or a computing device that instructs the user to look in an indicated direction in relation to the modified pre-recorded audio message being emitted by the speaker.
17 . The media device of claim 13 , wherein the video feed being active includes a camera of a computing device configured to capture video images of the user.
18 . The media device of claim 13 , wherein based on the video feed being inactive, the processor further causes the media device to display the contextual transcript on a display screen of the media device.
19 . The media device of claim 13 , wherein based on the video feed being inactive, the processor further causes the media device to:
mute the conference call; and
record the audio message of the user while the conference call is muted.
20 . The method of claim 1 , further comprising:
displaying an additional prompt on a media device instructing the user to look in an indicated direction of the modified pre-recorded audio message being emitted by the external speaker.