Machine learning-based audio codec switching
Described herein are techniques, devices, and systems for selectively using a music-capable audio codec on-demand during a communication session. A user equipment (UE) may adaptively transition between using a first audio codec that provides a first audio bandwidth and a second audio codec (e.g., the EVS-FB codec) that provides a second audio bandwidth that is greater than the first audio bandwidth. The transition to the second audio codec may occur in response to determining that sound in the environment of the UE includes frequencies outside of a range of frequencies associated with a human voice, such as by determining that music is being played in the environment of the UE, which allows for selectively using a music-capable audio codec when it would be beneficial to do so.
1. A computer-implemented method comprising:
establishing, by a user equipment (UE), and via a serving base station, a voice call using a first Enhanced Voice Services (EVS) audio codec that provides a first audio bandwidth;
determining, by the UE, that music is being played in an environment of the UE;
sending, by the UE, and based at least in part on the determining that the music is being played in the environment, a message to the serving base station for transitioning from using the first EVS audio codec to using a second EVS audio codec that provides a second audio bandwidth greater than the first audio bandwidth; and
continuing, by the UE, and via the serving base station, the voice call using the second EVS audio codec.
2. The computer-implemented method of claim 1 , wherein the second EVS audio codec is an EVS Full Band (EVS-FB) codec.
3. The computer-implemented method of claim 1 , further comprising, in response to the determining that the music is being played in the environment:
outputting, via the UE, a user prompt indicating that the UE detected background music and associated with transitioning from using the first EVS audio codec to using the second EVS audio codec; and
receiving user input via the UE to transition from using the first EVS audio codec to using a second EVS audio codec,
wherein the sending of the message occurs in response to the receiving of the user input.
4. The computer-implemented method of claim 1 , further comprising, after the continuing the voice call using the second EVS audio codec:
determining, by the UE, that the music is no longer being played in the environment;
sending, by the UE, and based at least in part on the determining that the music is no longer being played in the environment, a second message to the serving base station for transitioning from using the second EVS audio codec to using the first EVS audio codec; and
continuing, by the UE, and via the serving base station, the voice call using the first EVS audio codec.
5. The computer-implemented method of claim 4 , further comprising, in response to the determining that the music is no longer being played in the environment:
outputting, via the UE, a second user prompt indicating that the UE has ceased detecting background music and associated with transitioning from using the second EVS audio codec to using the first EVS audio codec; and
receiving second user input via the UE to transition from using the second EVS audio codec to using the first EVS audio codec,
wherein the sending of the second message occurs in response to the receiving of the second user input.
6. The computer-implemented method of claim 1 , further comprising:
determining, by the UE, and during the voice call, that a value indicative of a radio frequency (RF) condition is equal to or greater than a threshold value,
wherein the sending of the message is further based on the determining that the value indicative of the RF condition is equal to or greater than the threshold value.
7. A user equipment (UE) comprising:
a processor; and
memory storing computer-executable instructions that, when executed by the processor, cause the UE to:
establish, via a serving base station, a communication session using a first audio codec that provides a first audio bandwidth;
determine that sound in an environment of the UE includes frequencies outside of a range of frequencies associated with a human voice;
send, based at least in part on determining that the sound includes the frequencies outside of the range of frequencies associated with the human voice, a message to the serving base station for transitioning from using the first audio codec to using a second audio codec that provides a second audio bandwidth greater than the first audio bandwidth; and
continue, via the serving base station, the communication session using the second audio codec.
8. The UE of claim 7 , wherein the second audio codec is an Enhanced Voice Services Full Band (EVS-FB) codec.
9. The UE of claim 7 , wherein the computer-executable instructions, when executed by the processor, further cause the UE to, in response to determining that the sound includes the frequencies outside of the range of frequencies associated with the human voice:
output a user prompt associated with transitioning from using the first audio codec to using the second audio codec; and
receive user input to transition from using the first audio codec to using a second audio codec,
wherein sending the message occurs in response to receiving the user input.
10. The UE of claim 9 , wherein:
the user prompt requests a selection of a bit rate among multiple available bit rates to use with the second audio codec;
receiving the user input comprises receiving the selection of the bit rate as a selected bit rate; and
continuing the communication session using the second audio codec comprises using the second audio codec at the selected bit rate.
11. The UE of claim 7 , wherein sending the message occurs without user intervention in response to determining that the sound includes the frequencies outside of the range of frequencies associated with the human voice.
12. The UE of claim 7 , wherein the message includes a capability indicator indicating that the UE supports the second audio codec, and wherein continuing the communication session using the second audio codec is based at least in part on a second UE involved in the communication session also supporting the second audio codec.
13. The UE of claim 7 , wherein determining that the sound includes the frequencies outside of the range of frequencies associated with the human voice comprises determining that music is being played in the environment.
14. The UE of claim 13 , wherein the determining that the music is being played in the environment comprises:
providing audio data based on the sound as input to a trained machine learning model; and
generating, as output from the trained machine learning model, a probability that a source of the sound is not the human voice.
15. A computer-implemented method comprising:
establishing, by a user equipment (UE), and via a serving base station, a communication session using a first audio codec that provides a first audio bandwidth;
determining, by the UE, that sound in an environment of the UE includes frequencies outside of a range of frequencies associated with a human voice;
sending, by the UE, and based at least in part on determining that the sound includes the frequencies outside of the range of frequencies associated with the human voice, a message to the serving base station for transitioning from using the first audio codec to using a second audio codec that provides a second audio bandwidth greater than the first audio bandwidth; and
continuing, by the UE, and via the serving base station, the communication session using the second audio codec.
16. The computer-implemented method of claim 15 , wherein:
the first audio codec is at least one of:
an Enhanced Voice Services Wideband (EVS-WB) codec; or
an Enhanced Voice Services Super Wideband (EVS-SWB) codec; and
the second audio codec is an Enhanced Voice Services Full Band (EVS-FB) codec.
17. The computer-implemented method of claim 15 , further comprising:
determining, by the UE, and during the communication session, that a value indicative of a radio frequency (RF) condition is equal to or greater than a threshold value,
wherein the sending of the message is further based on the determining that the value indicative of the RF condition is equal to or greater than the threshold value.
18. The computer-implemented method of claim 15 , wherein the communication session is established using the first audio codec as a default codec.
19. The computer-implemented method of claim 15 , wherein the determining that the sound includes the frequencies outside of the range of frequencies associated with the human voice comprises determining that music is being played in the environment.
20. The computer-implemented method of claim 19 , further comprising, after the continuing the communication session using the second audio codec:
determining, by the UE, that the music is no longer being played in the environment;
sending, by the UE, and based at least in part on the determining that the music is no longer being played in the environment, a second message to the serving base station for transitioning from using the second audio codec to using the first audio codec; and
continuing, by the UE, and via the serving base station, the communication session using the first audio codec.