Synthetically generating inner speech training data

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:
• accessing a collection of overt speech signals representing phonemes, phoneme sounds, words or phrases spoken at least partially using overt speech;
• establishing a relationship between electromyograph (EMG) data corresponding to a first training set of overt speech segments, EMG data corresponding to a second training set of inner speech segments, and a third training set of rest data;
• transforming, based on the relationship, the collection of overt speech signals into inner speech training data comprising EMG data representing inner speech corresponding to the phonemes, phoneme sounds, words or phrases spoken at least partially using the overt speech;
• and
• training a machine learning model to decode inner speech signals into a set of corresponding phonemes, phoneme sounds, words or phrases based on the inner speech training data.

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:

• accessing a collection of overt speech signals representing phonemes, phoneme sounds, words or phrases spoken at least partially using overt speech;
• establishing a relationship between electromyograph (EMG) data corresponding to a first training set of overt speech segments, EMG data corresponding to a second training set of inner speech segments, and a third training set of rest data;
• transforming, based on the relationship, the collection of overt speech signals into inner speech training data comprising EMG data representing inner speech corresponding to the phonemes, phoneme sounds, words or phrases spoken at least partially using the overt speech;
• and
• training a machine learning model to decode inner speech signals into a set of corresponding phonemes, phoneme sounds, words or phrases based on the inner speech training data.