Silent speech detection with audio feedback
A system for generating audio feedback to silent speech, the system including a speaker and processing circuitry, the processing circuitry configured to (i) generate speech output including the articulated words of a test subject from sensed movements of skin of a face of the test subject in response to words articulated silently by the test subject and without contacting the skin, (ii) convert the speech output into an audio output, (iii) convey the audio output to the speaker as audio feedback while reducing latency, and (iv) play the audio feedback with reduced latency to the test subject on the speaker.
1 . A system for generating audio feedback to silent speech, the system comprising:
a speaker; and
processing circuitry, which is configured to:
generate speech output including the articulated words of a test subject from sensed movements of skin of a face of the test subject in response to words articulated silently by the test subject and without contacting the skin;
convert the speech output into an audio output;
convey the audio output to the speaker as audio feedback while reducing latency; and
play the audio feedback with reduced latency to the test subject on the speaker.
2 . The system according to claim 1 , wherein the processing circuitry is configured to reduce latency by achieving 25 mS latency.
3 . The system according to claim 1 , wherein the speaker is comprised in a wearable device.
4 . The system according to claim 1 , wherein the speaker and the processing circuitry are comprised in a wearable device.
5 . The system according to claim 1 , wherein the processing circuitry is configured to generate the audio output with the reduced latency by:
running a feature extraction (FE) algorithm to generate FE output;
inputting the FE output to a neural network (NN) algorithm;
running the NN algorithm to generate speech data output; and
inputting the speech data output to an inter-integrated sound (I 2 S) interface to generate the audio output with the reduced latency.
6 . The system according to claim 1 , wherein the processing circuitry is comprised in a wearable device.
7 . The system according to claim 6 , wherein the wearable device comprises an earpiece.
8 . The system according to claim 1 , wherein the processing circuitry is configured to convey the audio output to the speaker as audio feedback while reducing latency by using a split architecture system for detecting facial skin micromovements for speech detection, comprising:
a first device configured to perform a first subset of functionalities associated with detecting facial skin micromovements for determining non-vocalized speech, the first device comprising the circuitry configured to provide audio feedback while reducing latency; and
at least one second device paired with the first device and configured to perform a second subset of functionalities associated with detecting facial skin micromovements for determining non-vocalized speech, in coordination with the first device; and
convey the audio output to the speaker as audio feedback while reducing latency.
9 . The system according to claim 8 , wherein the first device comprises an earbud.
10 . A method for generating audio feedback to silent speech, the method comprising:
generating speech output including the articulated words of a test subject from sensed movements of skin of a face of the test subject in response to words articulated silently by the test subject and without contacting the skin;
converting the speech output into an audio output;
conveying the audio output to a speaker as audio feedback while reducing latency; and
playing the audio feedback with reduced latency to the test subject on the speaker.
11 . The method according to claim 10 , wherein reducing latency consists of achieving 25 mS latency.
12 . The method according to claim 10 , wherein the speaker is comprised in a wearable device.
13 . The method according to claim 10 , wherein the speaker and the processing circuitry are comprised in a wearable device.
14 . The method according to claim 10 , wherein generating the audio output with the reduced latency comprises:
running a feature extraction (FE) algorithm to generate FE output;
inputting the FE output to a neural network (NN) algorithm;
running the NN algorithm to generate speech data output; and
inputting the speech data output to an inter-integrated sound (I2S) interface to generate the audio output with the reduced latency.
15 . The method according to claim 10 , wherein generating the speech output, converting the speech output into the audio output, and conveying the audio output to a speaker is performed in a wearable device.
16 . The method according to claim 15 , wherein the wearable device comprises an earpiece.
17 . The method according to claim 10 , wherein conveying the audio output to the speaker as audio feedback while reducing latency comprises using a split architecture system for detecting facial skin micromovements for speech detection, comprising:
a first device configured to perform a first subset of functionalities associated with detecting facial skin micromovements for determining non-vocalized speech, the first device comprising the circuitry configured to provide audio feedback while reducing latency; and
at least one second device paired with the first device and configured to perform a second subset of functionalities associated with detecting facial skin micromovements for determining non-vocalized speech, in coordination with the first device; and
convey the audio output to the speaker as audio feedback while reducing latency.
18 . The method according to claim 17 , wherein the first device comprises an earbud.