Home automation having user privacy protections
An acoustic sensor is positioned in an environment and configured to generate a data stream responsive to acoustic energy in the environment. A controller is configured to receive the data stream. The controller is further configured to analyze the data stream to determine ambient acoustic signals. The controller is further configured to generate an ambient acoustic template based on the determined ambient acoustic signals. The controller is further configured to apply the ambient acoustic template to the data stream so that the ambient acoustic signals are suppressed in the data stream. The controller is further configured to analyze the data stream after the ambient acoustic signals are suppressed in order to determine if the acoustic energy in the environment includes acoustic energy of human snoring. The controller is further configured to issue a control signal to a second controller in order to engage a home automation device.
1. A system comprising:
an acoustic sensor positioned in an environment and configured to generate a data stream responsive to acoustic energy in the environment;
a controller communicably coupled to the acoustic sensor and configured to:
receive the data stream from the acoustic sensor in a short-term storage different than a long-term storage without storing the data stream in the long-term storage, the short-term storage configured to overwrite stored information with new received information;
analyze the data stream to determine ambient acoustic signals that are in the environment;
generate an ambient acoustic template based on the determined ambient acoustic signals that are in the environment;
apply the ambient acoustic template to the data stream so that the ambient acoustic signals are suppressed in the data stream;
store the data stream in the long-term storage after the ambient acoustic signals are suppressed such that no unsuppressed ambient signals are stored in the long-term storage;
analyze the data stream after the ambient acoustic signals are suppressed in order to determine if the acoustic energy in the environment includes acoustic energy of human snoring; and
responsive to determining if the acoustic energy in the environment includes acoustic energy of human snoring, issue a control signal to a second controller in order to engage a home automation device.
2. The system of claim 1 , wherein to analyze the data stream to determine ambient acoustic signals that are in the environment; and generate an ambient acoustic template based on the determined ambient acoustic signals that are in the environment, the controller is configured to:
segment the data stream, before the ambient acoustic signals are suppressed, into frames; and
performing a statistical analysis of multiple frames based on one or more parameters of properties of the frames; and
generate the template based on the statistical analysis.
3. The system of claim 2 , wherein one of the one or more parameters is frame energy.
4. The system of claim 2 , wherein the statistical analysis of multiple frames based on one or more parameters of properties of the frames comprises combining magnitude spectrums of low-energy frames among a plurality of frames.
5. The system of claim 4 , wherein combining magnitude spectrums of low-energy frames among a plurality of frames comprises selecting N frames for combination based on the N frames having the N-lowest energy values.
6. The system of claim 4 , wherein combining magnitude spectrums of low-energy frames among a plurality of frames comprises selecting frames for combination based on the selected frames having an energy value below a threshold value.
7. The system of claim 2 , where the statistical analysis of multiple frames based on one or more parameters of properties of the frames comprises:
identifying a subset of frames free from acoustic energy from speech; and
combining magnitude spectrums of the subset of frames identified as free from acoustic energy from speech.
8. The system of claim 2 , wherein to generate the template based on the statistical analysis, the controller is configured to find a mean of magnitude spectrums of the multiple frames.
9. The system of claim 8 , wherein the mean is a weighted mean that increases the weight of frames having low energy.
10. The system of claim 1 , wherein the data stream, after the ambient acoustic signals are suppressed, is subject to a filter to reduce an acoustic component generated by speech.
11. The system of claim 10 , wherein audio presentation of the data stream subjected contains no intelligible speech sounds.
12. The system of claim 1 , wherein the operations are performed responsive to a determination of user presence in a bed.
13. A system comprising:
an acoustic sensor positioned in an environment and configured to generate a data stream responsive to acoustic energy in the environment including acoustic energy of human snoring;
a controller communicably coupled the acoustic sensor and configured to:
receive the data stream from the acoustic sensor in a short-term storage different than a long-term storage without storing the data stream in the long-term storage, the short-term storage configured to overwrite stored information with new received information;
process the data stream to reduce acoustic components generated by speech;
store, in the long-term storage, the data stream with the acoustic components generated by speech reduced such that no unreduced speech is stored in the long-term storage;
apply encryption to the data stream with the acoustic components generated by speech reduced to create an encrypted data stream; and
transmit the encrypted data stream to a remote storage, or a cloud database.
14. The system of claim 13 , the controller further configured to:
determine, from the data stream after the data stream has been processed, presence of snore and an intensity of snore.
15. The system of claim 13 , wherein to apply encryption to the data stream to create an encrypted data stream, the controller is further configured to apply compression to the data stream.
16. The system of claim 13 , wherein to process the data stream to reduce acoustic components generated by speech, the controller is configured to apply a band pass filter with a frequency range of 100 to 800 Hz.
17. The system of claim 13 , wherein to process the data stream to reduce acoustic components generated by speech, the controller is configured to apply a band pass filter with a frequency range of 100 to 400 Hz.
18. The system of claim 13 , wherein to process the data stream to reduce acoustic components generated by speech, the controller is configured to apply a band pass filter with a frequency range of 0 to 800 Hz.