Inner speech production performance measurement and quantification
AssigneeSnap Inc.
InventorsElizabeth Izakson, Meir Meshulam, Hagar Yamin, Assif Ziv
Life of this patent
Estimating the term…
Abstract
Methods and systems are disclosed for measuring and quantifying inner speech production. The methods and systems present an instruction to a user to produce inner speech and collect electromyograph (EMG) data corresponding to the inner speech. The methods and systems process the EMG data by a machine learning model to generate a prediction comprising a word or phrase corresponding to the inner speech and concurrently generate an evaluation of inner speech production and detection.
Claims20
A method comprising:
- presenting an instruction to a user to produce inner speech corresponding to a target word or phrase;
- collecting electromyograph (EMG) data corresponding to the inner speech;
- classifying the EMG data by a machine learning model to generate a prediction corresponding to the inner speech;
- and
- concurrently generating an evaluation of inner speech production and detection, wherein the evaluation is presented to the user in a graphical user interface as feedback indicating whether the prediction generated by the machine learning model correctly matches the target word or phrase.
A system comprising:
- at least one processor;
- and
- at least one memory component having instructions stored thereon that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
- presenting an instruction to a user to produce inner speech corresponding to a target word or phrase;
- collecting electromyograph (EMG) data corresponding to the inner speech;
- classifying the EMG data by a machine learning model to generate a prediction corresponding to the inner speech;
- and
- concurrently generating an evaluation of inner speech production and detection, wherein the evaluation is presented to the user in a graphical user interface as feedback indicating whether the prediction generated by the machine learning model correctly matches the target word or phrase.
A non-transitory computer-readable storage medium having stored thereon instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
- presenting an instruction to a user to produce inner speech corresponding to a target word or phrase;
- collecting electromyograph (EMG) data corresponding to the inner speech;
- classifying the EMG data by a machine learning model to generate a prediction corresponding to the inner speech;
- and
- concurrently generating an evaluation of inner speech production and detection, wherein the evaluation is presented to the user in a graphical user interface as feedback indicating whether the prediction generated by the machine learning model correctly matches the target word or phrase.
Dependencies are inferred from the claim text.