# US 2026/0100138 A1 · Methods and systems for personalized adaptive auditory training > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0100138 A1 - Document ID: US20260100138A1 - Status: Published application - Kind: A1 - Application number: 19/327,703 - Filed: 2025-09-12 - Published: 2026-04-09 - Earliest claimed: 2024-10-08 - Assignees: Neurotone AI, Inc. - Applicants: Neurotone AI, Inc. - Inventors: Miles Aron; Travis Whitton; Rick Carlson; Robert Sweetow; Jennifer Henderson Sabes - Web page: https://patentgrep.com/patent/US20260100138A1 ## CPC - G09B 5/04: with audible presentation of the material to be studied (sound recording or reproducing G11B) - G10L 13/027: Concept to speech synthesisers; Generation of natural phrases from machine-based concepts (generation of parameters for speech synthesis out of text G10L13/08) - G10L 13/033: Voice editing, e.g. manipulating the voice of the synthesiser - G10L 25/66: for extracting parameters related to health condition (detecting or measuring for diagnostic purposes A61B5/00) - G09B: EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS (devices for psychotechnics or for testing reaction times A61B5/16; games, sports, amusements A63; projectors, projector screens G03B) - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract The present disclosure relates to adaptive auditory training systems and methods. A synthesized audio representation of an input text is generated and presented to a first user during a training session. Audio input from the first user corresponding to the input text is received, and a difficulty level of the synthesized audio representation is dynamically adjusted between consecutive prompts based on quantitative performance metrics derived from the received audio input. Acoustic thresholds are defined by signal-to-noise ratio measurements and response accuracy ranges, and difficulty adjustments may include modifying parameters such as timing, background noise level, word similarity, pitch, syllable count, or context clues. The synthesized audio representation may be personalized by training an artificial intelligence model on voice samples of a second user to create an emotion-agnostic voice clone preserving that user's speech characteristics. Outputs may include audiology diagnostics and actionable insights for providers in audiology and speech pathology. ## Claims ### Claim 1 A computer-implemented method of performing adaptive auditory training, comprising: generating a synthesized audio representation of an input text; presenting the synthesized audio representation to a first user during an auditory training session; receiving audio input from the first user corresponding to the input text; and dynamically adjusting a difficulty of the synthesized audio representation based on quantitative performance metrics derived from the received audio input to maintain training difficulty within target performance parameters, wherein adjusting the difficulty of the synthesized audio representation occurs between consecutive prompts during a same training session. ### Claim 2 (depends on 1) The method of claim 1, further comprising personalizing the synthesized audio representation by training an artificial intelligence model on voice samples of a second user to create a voice clone of the second user that preserves speech characteristics of the second user, wherein the synthesized audio representation is emotion-agnostic with neutral prosody. ### Claim 3 (depends on 1) The method of claim 1, wherein adjusting the difficulty of the synthesized audio representation includes modifying audio parameters including at least one of a time between words, a background noise level, a similarity between neighboring words, a number of syllables in words, a pitch of words, and a number of context clues. ### Claim 4 (depends on 1) The method of claim 1, wherein the quantitative performance metrics include at least one of QuickSIN SNR loss measurements, response latency data, signal-to-noise ratio measurements response accuracy ranges, and machine learning-generated performance scores. ### Claim 5 (depends on 1) The method of claim 1, wherein dynamically adjusting the difficulty further comprises: evaluating user response accuracy after each prompt; calculating acoustic threshold parameters using a psychometric staircase algorithm; selecting a next training stimulus based on the psychometric staircase calculations; and implementing the selected stimulus before presenting a next prompt. ### Claim 6 (depends on 1) The method of claim 1, wherein the input text is received from an interactive input text source comprising a chat session with an artificial intelligence chatbot. ### Claim 7 (depends on 1) The method of claim 1, wherein the input text is received from a dynamic input text source comprising at least one of a news feed and biblical passages. ### Claim 8 (depends on 1) The method of claim 1, further comprising generating, based on the dynamically adjusted difficulty synthesized audio representation, at least one of an audiology diagnostic and an actionable insight for providers in audiology and speech pathology. ### Claim 9 (depends on 1) The method of claim 1, wherein dynamically adjusting the difficulty of the synthesized audio representation comprises increasing a background noise level to simulate real-world listening environments. ### Claim 10 (depends on 1) The method of claim 1, wherein presenting the synthesized audio representation includes combining a first audio stream comprising the synthesized audio representation with a first audio stream comprising generic background noise stored in a pre-curated noise library. ### Claim 11 A system, comprising: a processing unit; a memory operatively coupled to the processing unit, the memory storing; a text-to-speech module operable to generate a synthesized audio representation of an input text; a dynamic adjustment module operable to dynamically adjust a difficulty of the synthesized audio representation based on quantitative performance metrics derived from the received audio input to maintain training difficulty within target performance parameters, wherein adjusting the difficulty of the synthesized audio representation occurs between consecutive prompts during a same training session; and a patient apps module operable to present the synthesized audio representation to a first user and receive audio input from the first user corresponding to the input text. ### Claim 12 (depends on 11) The system of claim 11, further comprising a personalization module operable to personalize the synthesized audio representation by training an artificial intelligence model on voice samples of a second user to create a voice clone of the second user that preserves speech characteristics of the second user, wherein the synthesized audio representation is emotion-agnostic with neutral prosody. ### Claim 13 (depends on 11) The system of claim 11, wherein adjusting the difficulty of the synthesized audio representation includes modifying audio parameters including at least one of a time between words, a background noise level, a similarity between neighboring words, a number of syllables in words, a pitch of words, and a number of context clues. ### Claim 14 (depends on 11) The system of claim 11, wherein the quantitative performance metrics include at least one of QuickSIN SNR loss measurements, response latency data, signal-to-noise ratio measurements response accuracy ranges, and machine learning-generated performance scores. ### Claim 15 (depends on 11) The system of claim 11, wherein the dynamic adjustment module is operable to: evaluate user response accuracy after each prompt; calculate acoustic threshold parameters using psychometric staircase algorithms; select a next training stimulus based on the psychometric staircase calculations; and implement the selected stimulus before presenting the next prompt. ### Claim 16 (depends on 11) The system of claim 11, wherein the input text is received from an interactive input text source comprising a chat session with an artificial intelligence chatbot. ### Claim 17 (depends on 11) The system of claim 11, wherein the input text is received from a dynamic input text source comprising at least one of a news feed and biblical passages. ### Claim 18 (depends on 11) The system of claim 11, wherein the dynamic adjustment module is operable to generate, based on the dynamically adjusted difficulty synthesized audio representation, at least one of an audiology diagnostic and an actionable insight for providers in audiology and speech pathology. ### Claim 19 (depends on 11) The system of claim 11, wherein dynamically adjusting the difficulty of the synthesized audio representation comprises increasing a background noise level to simulate real-world listening environments. ### Claim 20 (depends on 11) The system of claim 11, wherein the patient apps module is operable to present the synthesized audio representation to the first user by combining a first audio stream comprising the synthesized audio representation with a second audio stream comprising generic background noise stored in a pre-curated noise library.