Method and system for providing adjunct sensory information to a user
A method for providing information to a user, the method including: receiving an input signal from a sensing device associated with a sensory modality of the user; generating a preprocessed signal upon preprocessing the input signal with a set of preprocessing operations; extracting a set of features from the preprocessed signal; processing the set of features with a neural network system; mapping outputs of the neural network system to a device domain associated with a device including a distribution of haptic actuators in proximity to the user; and at the distribution of haptic actuators, cooperatively producing a haptic output representative of at least a portion of the input signal, thereby providing information to the user.
1. A system for providing information to a user, the system comprising:
a limb-worn device comprising an audio sensing device, wherein the audio sensing device receives an audio signal from an environment of the user;
a processing system, wherein the processing system:
processes the audio signal with a trained neural network model to determine a set of outputs;
maps the set of outputs to a set of tactile actuators arranged onboard the limb-worn device; and
the set of tactile actuators, wherein the set of tactile actuators cooperatively produces tactile sensation representative of the audio signal, thereby conveying information associated with the audio signal to the user at the limb-worn device.
2. The system of claim 1 , wherein the processing system is arranged onboard the limb-worn device.
3. The system of claim 2 , wherein the audio sensing device is a single microphone arranged onboard the limb-worn device.
4. The system of claim 1 , wherein mapping the set of outputs to the set of tactile actuators comprises mapping the set of outputs to a device domain associated with an arrangement of the set of tactile actuators.
5. The method of claim 4 , wherein the set of outputs comprises a set of phonemes, and wherein mapping the set of phonemes to the device domain comprises mapping multiple phonemes to a single tactile actuator of the set of tactile actuators.
6. The method of claim 1 , wherein the audio signal comprises high frequency audio, and wherein the trained model is configured to identify the high frequency audio.
7. The method of claim 6 , wherein the set of outputs comprises a set of high frequency phonemes.
8. The method of claim 7 , wherein the trained neural network model is configured to detect high frequency phonemes corresponding to speech, wherein the set of high frequency phonemes includes only the high frequency phonemes corresponding to speech.
9. The method of claim 1 , wherein the trained neural network model comprises a recurrent neural network.
10. The method of claim 9 , wherein the trained neural network model further comprises a Hidden Markov Model.
11. The method of claim 1 , wherein the set of tactile actuators comprises a plurality of tactile actuators, wherein the plurality of tactile actuators is arranged circumferentially about a band support structure of the limb-worn device, the band support structure operable to be positioned at a limb of the user.
12. A method for providing information to a user, the method comprising:
with a limb-worn device comprising an audio sensing device and a set of tactile actuators, receiving an audio signal at the audio sensing device from an environment of the user;
at a processing system in communication with the limb-worn device:
processing the audio signal with a trained neural network model to determine set of outputs;
mapping the set of outputs to the set of tactile actuators; and
with the set of tactile actuators, cooperatively producing tactile sensation representative of the audio signal, thereby conveying information associated with the audio signal to the user at the limb-worn device.
13. The method of claim 12 , wherein the trained neural network model comprises a recurrent neural network architecture and implements a statistical model for recognition of speech components from the audio signal.
14. The method of claim 13 , wherein trained neural network model further comprises a convolutional layer.
15. The method of claim 12 , wherein mapping the set of outputs to the set of tactile actuators comprises mapping the set of outputs to a device domain associated with an arrangement of the set of tactile actuators.
16. The method of claim 15 , wherein the set of outputs comprises a set of phonemes, and wherein mapping the set of phonemes to the device domain comprises mapping multiple phonemes to a single tactile actuator of the set of tactile actuators.
17. The method of claim 12 , wherein the audio signal comprises high frequency audio, and wherein the trained model is configured to identify the high frequency audio.
18. The method of claim 17 , wherein the set of outputs comprises a set of high frequency phonemes.
19. The method of claim 18 , wherein the trained neural network model is configured to detect high frequency phonemes corresponding to speech, wherein the set of high frequency phonemes is only high frequency phonemes corresponding to speech.
20. The method of claim 12 , wherein the audio sensing device is a single microphone arranged onboard the limb-worn device.