Respirator acoustic amelioration
An acoustic signal is received from a first user. The acoustic signal of the first user includes a verbal utterance related to the first user. A set of one or more non-verbal sensor readings may be detected from a set of one or more sensors of a wearable device. The wearable device is worn by the user concurrent with the verbal utterance. A verbal distortion factor may be determined based on an acoustic adjustment model and in response to the set of non-verbal sensor readings. An adjusted verbal utterance related to the first user may be generated. The adjusted verbal utterance may be generated from the verbal utterance and based on the verbal distortion factor. The adjusted verbal utterance may be provided to a voice output.
1. A method comprising:
receiving an acoustic signal from a first user, wherein the acoustic signal of the first user includes a verbal utterance related to the first user;
detecting, from a set of one or more sensors of a wearable device, a set of one or more non-verbal sensor readings, wherein the wearable device is worn by the user concurrent with the verbal utterance;
determining, based on an acoustic adjustment model and in response to the set of non-verbal sensor readings, a verbal distortion factor;
generating, from the verbal utterance and based on the verbal distortion factor, an adjusted verbal utterance related to the first user; and
providing, the adjusted verbal utterance, to a voice output.
2. The method of claim 1 , wherein the acoustic adjustment model includes a machine learning model, and wherein the determining the verbal distortion factor comprises:
inputting, to the machine learning model, the non-verbal sensor readings.
3. The method of claim 2 , the determining the verbal distortion factor comprises:
inputting, to the machine learning model, the verbal utterance.
4. The method of claim 2 , wherein the method further comprises:
updating the machine learning model based on prior verbal utterances of the first user.
5. The method of claim 2 , wherein the method further comprises:
updating the machine learning model based on prior verbal utterances of users other than the first user.
6. The method of claim 2 , wherein the machine learning model is trained based on the wearable device.
7. The method of claim 1 , wherein the wearable device is a respirator configured to filter an atmosphere around the user.
8. The method of claim 7 , wherein a first sensor of the one or more sensors is an air speed sensor coupled to an inside surface of the respirator.
9. The method of claim 8 , wherein a second sensor of the one or more sensors is an air speed sensor coupled to an outside surface of the respirator.
10. The method of claim 7 , wherein a first sensors of the one or more sensors is a vibration sensor.
11. The method of claim 1 , wherein the voice output is a transceiver of a client device.
12. The method of claim 1 , wherein the voice output is a network communication to a second user.
13. The method of claim 1 , wherein the voice output is a headphone communicatively coupled to a client device of the user.
14. The method of claim 1 , wherein the verbal utterance is received from a microphone, and wherein the receiving the acoustic signal comprises:
transmitting, by the microphone, the acoustic signal to a client device of the user.
15. A system, the system comprising:
a memory, the memory containing one or more instructions; and
a processor, the processor communicatively coupled to the memory, the processor, in response to reading the one or more instructions, configured to:
receive an acoustic signal from a first user, wherein the acoustic signal of the first user includes a verbal utterance related to the first user;
detect, from a set of one or more sensors of a wearable device, a set of one or more non-verbal sensor readings, wherein the wearable device is worn by the user concurrent with the verbal utterance;
determine, based on an acoustic adjustment model and in response to the set of non-verbal sensor readings, a verbal distortion factor;
generate, from the verbal utterance and based on the verbal distortion factor, an adjusted verbal utterance related to the first user; and
provide, the adjusted verbal utterance, to a voice output.
16. The system of claim 15 , wherein the acoustic adjustment model includes a machine learning model, and wherein the determine the verbal distortion factor comprises:
inputting, to the machine learning model, the non-verbal sensor readings.
17. The system of claim 15 , wherein the wearable device is a respirator configured to filter an atmosphere around the user.
18. A computer program product, the computer program product comprising:
one or more computer readable storage media; and
program instructions collectively stored on the one or more computer readable storage media, the program instructions configured to:
receive an acoustic signal from a first user, wherein the acoustic signal of the first user includes a verbal utterance related to the first user;
detect, from a set of one or more sensors of a wearable device, a set of one or more non-verbal sensor readings, wherein the wearable device is worn by the user concurrent with the verbal utterance;
determine, based on an acoustic adjustment model and in response to the set of non-verbal sensor readings, a verbal distortion factor;
generate, from the verbal utterance and based on the verbal distortion factor, an adjusted verbal utterance related to the first user; and
provide, the adjusted verbal utterance, to a voice output.
19. The computer program product of claim 18 , wherein the acoustic adjustment model includes a machine learning model, and wherein the determine the verbal distortion factor comprises:
inputting, to the machine learning model, the non-verbal sensor readings.
20. The computer program product of claim 18 , wherein the wearable device is a respirator configured to filter an atmosphere around the user.