EMG Voice Restoration

This Phase I SBIR is prompted by the need for more effective Augmentative and Alternative CommunicationAACdevices for persons unable to communicate through vocalizationThe project follows our preliminary work that translates surface electromyographicsEMGsignals recorded from speech articulation muscles during silently mouthedsubvocalspeech to produce hands free intelligible textual communication on an Android or other AAC platformNow we undertake a first of its kind AAC system that restores personalizednatural expressive vocal communication through an advanced sEMG based neural interfaceThis innovation will have broad impact among millions of AAC users by restoring not only the vocabularybut the prosodic attributes of speech directly to personalized voice synthesis technologiesTo achieve this unprecedented goalour team of experts in sEMG based subvocal speech recognition at AltecInc will partner with VocalIDthe world s leading provider of personalized text to voice synthesis for AAC devicesIn Phase I we will develop algorithms for tracking sEMG based changes in prosody at the phrase level of subvocal speechAimsynthesize the prosodic changes into personalized digital voiceAimand establish the proof of principle that the sEMG based digitized voice can communicate phrases with declarativeinterrogative and contrastive prosody effectively in people with laryngectomya high need patient population that lacks the ability to vocalizeAimPhase II will advance the recognition of intonationloudness and timing at the triphone level of subvocal speech and directly synthesizein real timea personalizedintelligible and expressive voice that is capable of communicating meaningemotion and intentOur final deliverable will be an AAC system that is unique in restoring acoustic speech for those who live without their natural voiceThe device will be packaged as a wearable system that provides natural embodimentcosmetic appealand intuitive vocal capabilitiesIt will be hands freewill not suffer from poor intelligibilitywill not need surgical intervention or invasive maintenanceand will be readily adaptable to man machine interface for improved AAC controlThe impact of this innovation is that it will provide singular technology that restores personalized and prosodic vocal capabilities to the natural intuitive mechanisms of speech production for the vocally impaired NARRATIVE We propose a speech recognition system that uses noninvasive electromyographicEMGsignals from speech articulation muscles during subvocali emouthedspeech to restore the ability to communicate for those with vocal impairmentssuch as individual s post laryngectomyThe EMG Voice Restoration system will improve upon current methods of augmentative and alternative communicationAACtechnologies by offering a noninvasivehands free device that synthesizes a personalizedintelligible and expressive voice based entirely on the segmental and prosodic content recognized from the EMG recordingsThe impact will improve the quality of life for people with laryngectomyand lead to alternative methods for interfacing with computers and machines by people with other speech disorders or limited motor function