Speakerphone and server device for environment acoustics determination and related methods
A speakerphone is disclosed. The speakerphone comprises an interface, a speaker, one or more microphones including a first microphone, a processor, and a memory. The speakerphone is configured to obtain an internal output signal for provision of an internal audio output signal in an environment. The speakerphone is configured to output the internal audio output signal in the environment. The speakerphone is configured to obtain a microphone input signal. The speakerphone is configured to determine an impulse response associated with the environment. The speakerphone is configured to determine one or more environment parameters indicative of acoustics of the environment. The speakerphone is configured to transmit the impulse response and/or the first environment parameter to a server device.
1 . A speakerphone, the speakerphone comprising an interface, a speaker, and one or more microphones including a first microphone, the speakerphone comprising a processor and a memory, wherein the speakerphone is configured to:
obtain, using the processor, an internal output signal for provision of an internal audio output signal in an environment;
output, using the speaker and based on the internal output signal, the internal audio output signal in the environment;
obtain, using the first microphone, a microphone input signal, wherein the microphone input signal is a resulting signal after the internal audio output signal is outputted by the speaker in the environment;
determine, using the processor and based on the internal output signal and the microphone input signal, an impulse response associated with the environment;
determine, using the processor and based on the impulse response, one or more environment parameters indicative of acoustics of the environment, the one or more environment parameters including a first environment parameter;
transmit, via the interface, one or both of the impulse response and the first environment parameter to a server device.
2 . Speakerphone according to claim 1 , wherein the speakerphone is configured to obtain an environment configuration associated with the environment and to transmit the environment configuration to the server device.
3 . Speakerphone according to claim 2 , wherein the speakerphone is configured to obtain a user input indicative of one or more properties of the environment, and wherein the environment configuration is based on the user input.
4 . Speakerphone according to claim 1 , wherein the processor comprises machine learning circuitry configured to operate according to a machine learning model, wherein to determine the one or more environment parameters comprises to determine the one or more environment parameters, based on the impulse response, using the machine learning model.
5 . Speakerphone according to claim 1 , wherein the speakerphone is configured to determine, based on the first environment parameter, an environment score indicative of suitability of a conference setup in the environment and to transmit the environment score to the server device.
6 . Speakerphone according to claim 1 , wherein the speakerphone is configured to determine, based on the first environment parameter, a conference setup recommendation; and wherein the speakerphone is configured to transmit the conference setup recommendation to the server device.
7 . Speakerphone according to claim 1 , wherein the speakerphone is configured to determine a background noise parameter, and wherein the speakerphone is configured to determine, based on the first environment parameter and the background noise parameter, the environment score.
8 . Speakerphone according to claim 1 , wherein to obtain the internal output signal comprises to obtain a far-end input signal from a far-end communication device; and wherein the internal output signal is based on the far-end input signal.
9 . Speakerphone according to claim 1 , wherein the processor comprises a speech detector module configured to detect speech based on the microphone input signal.
10 . Speakerphone according to claim 9 , wherein the speakerphone is configured to, in accordance with a detection of no speech and a detection of no internal output signal, determine a background noise parameter, and in accordance with a detection of speech and a detection of no internal output signal, determine a speech parameter, and wherein the speakerphone is configured to determine a signal-to-noise ratio based on the background noise parameter and the speech parameter, and wherein the speakerphone is configured to determine, based on the first environment parameter and the signal-to-noise ratio, the environment score.
11 . Speakerphone according to claim 1 , wherein the speakerphone is configured to determine, based on the impulse response, one or more of: a first parameter indicative of a first reflection characteristic, a second parameter indicative of a second reflection characteristic, and a third parameter indicative of a third reflection characteristic; and wherein the first environment parameter is based on one or more of: the first parameter, the second parameter, and the third parameter, and wherein the speakerphone is configured to transmit, via the interface, one or more of the first parameter, the second parameter, and the third parameter.
12 . Speakerphone according to claim 11 , wherein the first parameter is a reverberation time, the second parameter is a direct-to-reverberant ratio, and/or the third parameter is an early decay time.
13 . Speakerphone according to claim 1 , wherein the first environment parameter is indicative of a size of the environment, a volume of the environment, a level of absorption of the environment, or a position of the speakerphone in the environment.
14 . Speakerphone according to claim 1 , wherein to obtain the internal output signal comprises to obtain a test signal; and wherein the internal output signal is based on the test signal.
15 . Speakerphone according to claim 14 , wherein the speakerphone is configured to determine the impulse response based on the test signal.
16 . A system comprising one or more speakerphones including a speakerphone according to claim 1 and a server device comprising one or more processors comprising machine learning circuitry configured to operate according to a machine learning model, one or more interfaces, and a memory, wherein the server device is configured to:
obtain, via the one or more interfaces, from the speakerphone according to claim 1 , one or both of an impulse response associated with an environment and one or more environment parameters indicative of acoustics of the environment;
train the machine learning model based on one or both of the impulse response and the one or more environment parameters for provision of an updated machine learning model; and
transmit the updated machine learning model to at least one of the one or more speakerphones.
17 . A server device comprising one or more processors comprising machine learning circuitry configured to operate according to a machine learning model, one or more interfaces, and a memory, wherein the server device is configured to:
obtain, via the one or more interfaces, from one or more speakerphones, one or both of an impulse response associated with an environment and one or more environment parameters indicative of acoustics of the environment;
train the machine learning model based on one or both of the impulse response and the one or more environment parameters for provision of an updated machine learning model; and
transmit the updated machine learning model to at least one of the one or more speakerphones.
18 . Server device according to claim 17 , wherein the server device is configured to:
determine, based on one or both of the impulse response and the one or more environment parameters, a simulated impulse response associated with a simulated environment; and
train the machine learning model based on the simulated impulse response for provision of an updated machine learning model; and
transmit the updated machine learning model to at least one of the one or more speakerphones.
19 . Server device according to claim 17 , wherein the updated machine learning model is an echo canceller model, and wherein the server device is configured to transmit the updated machine learning model to at least one of the one or more speakerphones.
20 . A method of operating a speakerphone system comprising one or more speakerphones including a first speakerphone comprising a processor, a memory, an interface, a speaker, and one or more microphones including a first microphone, and a server device, the method comprising:
obtaining, using the first speakerphone, an internal output signal for provision of an internal audio output signal in an environment;
outputting, using the first speakerphone and based on the internal output signal, an internal audio output signal in the environment;
obtaining, using the first speakerphone, a microphone input signal, wherein the microphone input signal is a resulting signal after the internal audio output signal is outputted by the speaker in the environment;
determining, using the first speakerphone and based on the internal output signal and the microphone input signal, an impulse response associated with the environment;
determining, using the first speakerphone, based on the impulse response, one or more environment parameters indicative of acoustics of the environment, the one or more environment parameters including a first environment parameter;
transmitting, from the first speakerphone, one or both impulse response and the first environment parameter to the server device.