Natural language processing while sound sensor is muted

1. An apparatus comprising:

a sound sensor;

an audio output device;

one or more communication interfaces;

one or more processor devices coupled to the sound sensor, the audio output device and the one or more communication interfaces; and

one or more memory devices coupled to the one or more processor devices and storing instructions executable by the one or more processor devices to:

receive a mute data setting indicating a muted or unmuted state of a first voice communication session with a first party from a user;

generate first audio data based on sound detected by the sound sensor at a first time;

initiate transmission, via the one or more communication interfaces, of the first audio data to another device during the first voice communication session based on a determination that the sound sensor is unmuted with respect to the first voice communication session at the first time based on the state of the mute data setting indicating unmuted;

generate second audio data based on sound detected by the sound sensor at a second time;

refrain from initiating transmission of the second audio data to the other device during the first voice communication session based on a determination that the sound sensor is muted with respect to the first voice communication session at the second time based on the state of the mute data setting indicating muted;

initiate a natural language processing operation on the second audio data based on detecting a wake phrase in the second audio data, including initiating transmission, via the one or more communication interfaces, of the second audio data to a remote natural language processing device;

initiate a second voice communication session with a second party, via the one or more communication interfaces, based on a response from the natural language processing device to a spoken command detected in the second audio data;

initiate transmission, via the one or more communication interfaces, of second audio data to a device of the second party during the second voice communication session based on a determination that the sound sensor is muted with respect to the first voice communication session at the second time based on the state of the mute data setting indicating muted without placing the first voice communication session on hold;

initiate output, via the audio output device, of sound based on communication data received, via the one or more communication interfaces, from the other device during the first voice communication session and based on output data received, via the one or more communication interfaces, from the device of the second party during the second voice communication session; and

conduct the first voice communication session and the second voice communication session in parallel.

2. The apparatus of claim 1 , wherein the second voice communication session is associated with an emergency service.

3. The apparatus of claim 1 , wherein initiating the natural language processing operation includes storing, in the one or more memory devices, a note associated with the first voice communication session based on a spoken command detected in the second audio data.

4. The apparatus of claim 1 , wherein the second audio data includes the wake phrase.

5. A computer readable storage device storing instructions, the instructions executable by one or more processor devices to:

receive a mute data setting indicating a muted or unmuted state of a first voice communication session with a first party from a user;

generate first audio data based on sound detected by a sound sensor at a first time;

initiate transmission, via one or more communication interfaces, of the first audio data to another device during the first voice communication session based on a determination that the sound sensor is unmuted with respect to the first voice communication session at the first time based on the state of the mute data setting indicating unmuted;

generate second audio data based on sound detected by the sound sensor at a second time;

refrain from initiating transmission of the second audio data to the other device during the first voice communication session based on a determination that the sound sensor is muted with respect to the first voice communication session at the second time based on the state of the mute data setting indicating muted;

initiate a natural language processing operation on the second audio data based on detecting a wake phrase in the second audio data, including initiating transmission, via the one or more communication interfaces, of the second audio data to a remote natural language processing device;

initiate a second voice communication session with a second party, via the one or more communication interfaces, based on a response from the natural language processing device to a spoken command detected in the second audio data;

initiate transmission, via the one or more communication interfaces, of second audio data to a device of the second party during the second voice communication session based on a determination that the sound sensor is muted with respect to the first voice communication session at the second time based on the state of the mute data setting indicating muted without placing the first voice communication session on hold;

initiate output, via an audio output device, of sound based on communication data received, via the one or more communication interfaces, from the other device during the first voice communication session and based on output data received, via the one or more communication interfaces, from the device of the second party during the second voice communication session; and

conduct the first voice communication session and the second voice communication session in parallel.

6. The computer readable storage device of claim 5 , wherein the second voice communication session is associated with an emergency service.

7. The computer readable storage device of claim 5 , wherein initiating the natural language processing operation includes storing, in one or more memory devices, a note associated with the first voice communication session based on a spoken command detected in the second audio data.

8. The computer readable storage device of claim 5 , wherein the second audio data includes the wake phrase.

9. A method comprising:

receiving a mute data setting indicating a muted or unmuted state of a first voice communication session from a user;

generating first audio data based on sound detected by a sound sensor at a first time;

transmitting, via one or more communication interfaces, the first audio data to another device during the first voice communication session based on a determination that the sound sensor is unmuted with respect to the first voice communication session at the first time based on the state of the mute data setting indicating unmuted;

generating second audio data based on sound detected by the sound sensor at a second time;

refraining from transmitting the second audio data to the other device during the first voice communication session based on a determination that the sound sensor is muted with respect to the first voice communication session at the second time based on the state of the mute data setting indicating muted;

initiating a natural language processing operation on the second audio data based on detecting a wake phrase in the second audio data, including initiating transmission, via the one or more communication interfaces, of the second audio data to a remote natural language processing device;

initiating a second voice communication session to a second party, via the one or more communication interfaces, based on a response from the natural language processing device to a spoken command detected in the second audio data;

initiating transmission, via the one or more communication interfaces, of second audio data to a device of the second party during the second voice communication session based on a determination that the sound sensor is muted with respect to the first voice communication session at the second time based on the state of the mute data setting indicating muted without placing the first voice communication session on hold;

initiating output, via an audio output device, of sound based on communication data received, via the one or more communication interfaces, from the other device during the first voice communication session and based on output data received, via the one or more communication interfaces, from the device of the second party during the second voice communication session; and

conducting the first voice communication session and the second voice communication session in parallel.

10. The method of claim 9 , wherein the second voice communication session is associated with an emergency service.