Automatic volume control of a voice signal provided to a captioning communication service
Apparatuses and methods are disclosed for automatic volume control of an audio stream reproduced by a captioning communication service for use by a call assistant in generating a text transcription of a communication session between a hearing-impaired user and a far-end user. The automatic volume control automatically adjusts a volume of the audio stream reproduced by the captioning communication service responsive to a volume control command identifying which of the far-end voice signal and the near-end voice signal is active at a given time. The system further includes an echo modifier configured to add distortion to an echo portion of the far-end voice signal when generating the audio stream.
1. A communication device comprising:
a microphone configured to capture first sound and generate a near-end voice signal based on the first sound;
communication elements configured to receive a signal that includes a far-end voice signal obtained over a network and to direct an audio stream signal to a captioning communication system remote from the communication device, the audio stream signal based on the received signal; and
a computing system communicatively coupled to the microphone and the communication elements and configured to cause the communication device to perform operations, the operations comprising:
determine an activity of the received signal;
determine an activity of the near-end voice signal; and
automatically control a volume level of audio, which is based on the audio stream signal, produced by the captioning communication system based on the activity of the received signal and the activity of the near-end voice signal, the automatically controlling the volume level of the audio including reducing the volume level of the audio in response to the received signal being inactive and the near-end voice signal being active.
2. The communication device of claim 1 , wherein automatically controlling the volume level of the audio comprises generate a volume control command based on the activity of the near-end voice signal and the activity of the received signal, the communication device further comprising audio processing logic configured to obtain the volume control command and to adjust the volume level of the audio based on the volume control command to automatically control the volume level of the audio.
3. The communication device of claim 1 , wherein automatically controlling the volume level of the audio comprises:
generate a volume control command based on the activity of the near-end voice signal and the received signal; and
encode the audio stream signal with the volume control command in packets that are communicated to the captioning communication system to automatically control the volume level of the audio, the captioning communication system including audio processing logic configured to obtain the volume control command and to adjust the volume level of the audio based on the volume control command at the captioning communication system.
4. The communication device of claim 3 , wherein the volume control command is one of a binary flag or a numerical value.
5. The communication device of claim 1 , wherein the operations further comprise:
generate an estimated echo signal of an echo signal that is included in the received signal;
add distortion to the estimated echo signal to generate a modified estimated echo signal; and
generate the audio stream signal based on a summation of the modified estimated echo signal and the received signal.
6. The communication device of claim 5 , wherein adding distortion to the estimated echo signal includes performing at least one of the following with respect to the estimated echo signal: frequency shifting, signal modulation, attenuation, adding white noise, and adding colored noise.
7. The communication device of claim 1 , wherein the automatically controlling the volume level of the audio further includes setting the volume level to a first level in response to determining that received signal is active.
8. The communication device of claim 7 , wherein the automatically controlling the volume level of the audio further includes setting the volume level to a third level in response to both the near-end voice signal and the received signal being simultaneously active, the third level being different than the first level.
9. A method comprising:
determining an active talker situation responsive to comparing a near-end voice signal generated by a near-end communication device and a received signal based on a far-end voice signal derived from a far-end communication device;
generating, at the near-end communication device, an audio stream signal based on the received signal;
directing the audio stream signal to a captioning communication system remote from the near-end communication device; and
automatically controlling a volume level of audio, which is based on the audio stream signal, produced by the captioning communication system based on the determined active talker situation, the automatically controlling the volume level of the audio including reducing the volume level of the audio in response to the determined active talker situation indicating that the received signal is inactive and the near-end voice signal is active.
10. The method of claim 9 , wherein comparing the near-end voice signal and the received signal includes cross-correlating the received signal and the near-end voice signal.
11. The method of claim 9 , wherein the active talker situation is selected from the group consisting of: a near-end situation in which only the near-end voice signal is active, a far-end situation in which only the received signal is active, and a double talk situation in which both the near-end voice signal and the received signal are active.
12. The method of claim 9 , wherein automatically controlling the volume level of the audio comprises:
generating a volume control command indicating the determined active talker situation; and directing adjustment of the volume level of the audio based on the volume control command.
13. The method of claim 9 , wherein automatically controlling the volume level of the audio comprises:
generating a volume control command indicating the determined active talker situation; and
processing the audio stream signal according to the volume control command, prior to the audio being produced by the captioning communication system, to have a first volume level for a first active talker situation and a second volume level for a second active talker situation.
14. The method of claim 13 , wherein generating the volume control command is performed by the near-end communication device, and processing the audio stream signal is performed by the captioning communication system.
15. The method of claim 13 , wherein generating the volume control command and processing the audio stream signal are both performed by the captioning communication system.
16. The method of claim 13 , wherein generating the volume control command and processing the audio stream signal are both performed by the near-end communication device.
17. The method of claim 9 , further comprising:
estimating an echo portion of the received signal; and
adding distortion to the estimated echo portion to generate a modified estimated echo signal,
wherein the audio stream signal is generated based on the modified estimated echo signal and the received signal such that the audio stream signal is a modified version of the received signal that includes the echo portion.
18. The method of claim 9 , wherein automatically controlling the volume level of the audio comprises:
packetizing the audio stream signal with a volume control command determined based on the determined active talker situation; and
sending the packets to the captioning communication system in which the captioning communication system adjusts the volume level of the audio produced by the audio stream signal based on the volume control command.
19. A system comprising:
one or more non-transitory computer-readable media having instructions stored thereon; and
one or more processors communicatively coupled to the one or more computer-readable media and configured to, in response to executing the instructions, cause the system to perform operations, the operations comprising:
obtain, from a communication device remote from the system, an audio stream signal that is generated from a received signal that is received at the communication device over a network and that is based on a far-end voice signal generated by a far-end communication device; and
produce audio based on the audio stream signal in which a volume level of the produced audio is based on activity of the received signal at the communication device and based on activity of a near-end signal generated by the communication device based on sound captured by a microphone of the communication device, wherein the volume level of the produced audio is reduced in response to the received signal being inactive and the near-end signal being active.
20. The system of claim 19 , wherein the audio stream signal is based on a modified estimated echo signal that includes distortion added to an estimated echo signal of an echo signal included in the received signal.