Communication of transcriptions
View Patent ↗A method may include obtaining audio originating at a remote device during a communication session conducted between a first device and the remote device and obtaining a transcription of the audio. The method may also include processing the audio to generate processed audio. In some embodiments, the audio may be processed by a neural network that is trained with respect to an analog voice network and the processed audio may be formatted with respect to communication over the analog voice network. The method may further include processing the transcription to generate a processed transcription that is formatted with respect to communication over the analog voice network and multiplexing the processed audio with the processed transcription to obtain combined data. The method may also include communicating, to the first device during the communication session, the combined data over a same communication channel of the analog voice network.
1. A method comprising:
obtaining, at a system, audio originating at a remote device during an audio communication session conducted between a first device and the remote device, the first device and the remote device being separate and distinct from the system;
obtaining, at the system, a transcription of the audio;
processing, by the system, the audio to generate a first audio data signal, wherein the audio is processed by a neural network that is trained with respect to an analog voice network and wherein the first audio data signal is formatted with respect to communication over the analog voice network;
processing, by the system, the transcription to generate a second audio data signal that includes information from the transcription and that is formatted with respect to communication over the analog voice network;
multiplexing, by the system, the first audio data signal with the second audio data signal to generate a third audio data signal that includes both the first audio data signal and the second audio data signal; and
communicating, from the system to the first device during the audio communication session via the analog voice network, the third audio data signal over a same communication channel of the analog voice network.
2. The method of claim 1 , wherein:
the audio is processed such that the first audio data signal uses a first communication resource of the analog voice network and leaves a second communication resource of the analog voice network available for communication of the second audio data signal;
the first audio data signal of the third audio data signal is communicated over the communication channel using the first communication resource; and
the second audio data signal of the third audio data signal is communicated over the communication channel using the second communication resource.
3. The method of claim 2 , wherein the multiplexing is based on the first communication resource such that the first audio data signal of the third audio data signal uses the first communication resource and the second audio data signal of the third audio data signal uses the second communication resource.
4. The method of claim 1 , wherein the processing of the transcription is performed using the neural network.
5. The method of claim 1 , wherein the multiplexing is such that the first audio data signal of the third audio data signal and the second audio data signal of the third audio data signal are communicated using a same communication resource of the communication channel.
6. The method of claim 1 , wherein the multiplexing includes time multiplexing the first audio data signal and the second audio data signal.
7. The method of claim 1 , wherein the multiplexing includes frequency multiplexing the first audio data signal and the second audio data signal.
8. The method of claim 1 , further comprising training the neural network based on prior audio of one or more previous communication sessions.
9. The method of claim 1 , wherein the processing of the audio includes performing a bandwidth compression operation on the audio such that the first audio data signal uses less bandwidth than the audio prior to processing and wherein the processing of the transcription is based on bandwidth made available by the bandwidth compression operation.
10. The method of claim 1 , wherein the processing of the audio includes performing a time compression operation on the audio such that the first audio data signal occupies less time than the audio prior to processing and wherein the processing of the transcription is based on time made available by the time compression operation.
11. At least one non-transitory computer-readable media configured to store one or more instructions that, in response to being executed by at least one processor, cause or direct the system to perform the method of claim 1 .
12. A system comprising:
a memory configured to store instructions; and
one or more hardware processors coupled to the memory and configured to execute the instructions to cause or direct the system to perform operations, the operations comprising:
obtain audio originating at a remote device during an audio communication session conducted between a first device and the remote device, the first device and the remote device being separate and distinct from the system;
obtain a transcription of the audio;
process the audio to generate a first audio data signal, wherein the audio is processed by a neural network that is trained with respect to an analog voice network and wherein the first audio data signal is formatted with respect to communication over the analog voice network;
process the transcription to generate a second audio data signal that includes information from the transcription and that is formatted with respect to communication over the analog voice network;
multiplex the first audio data signal with the second audio data signal to generate a third audio data signal that includes both the first audio data signal and the second audio data signal; and
communicate, to the first device during the audio communication session via the analog voice network, the third audio data signal over a same communication channel of the analog voice network.
13. The system of claim 12 , wherein:
the audio is processed such that the first audio data signal uses a first communication resource of the analog voice network and leaves a second communication resource of the analog voice network available for communication of the second audio data signal;
the first audio data signal of the third audio data signal is communicated over the communication channel using the first communication resource; and
the second audio data signal of the third audio data signal is communicated over the communication channel using the second communication resource.
14. The system of claim 13 , wherein the multiplexing is based on the first communication resource such that the first audio data signal of the third audio data signal uses the first communication resource and the second audio data signal of the third audio data signal uses the second communication resource.
15. The system of claim 12 , wherein the processing of the transcription is performed using the neural network.
16. The system of claim 12 , wherein the multiplexing is such that the first audio data signal of the third audio data signal and the second audio data signal of the third audio data signal are communicated using a same communication resource of the communication channel.
17. The system of claim 12 , wherein the multiplexing includes time multiplexing the first audio data signal and the second audio data signal.
18. The system of claim 12 , wherein the multiplexing includes frequency multiplexing the first audio data signal and the second audio data signal.
19. The system of claim 12 , wherein the operations further comprise training the neural network based on prior audio of one or more previous communication sessions.
20. The system of claim 12 , wherein the processing of the audio includes performing one or more of:
a bandwidth compression operation on the audio such that the first audio data signal uses less bandwidth than the audio prior to processing and wherein the processing of the transcription is based on bandwidth made available by the bandwidth compression operation; and
a time compression operation on the audio such that the first audio data signal occupies less time than the audio prior to processing and wherein the processing of the transcription is based on time made available by the time compression operation.