# US 12,223,943 B2 · Assisted speech > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,223,943 B2 - Document ID: US12223943B2 - Status: Granted - Kind: B2 - Application number: 18/237,621 - Filed: 2023-08-24 - Published: 2024-02-08 - Granted: 2025-02-11 - Earliest claimed: 2019-06-27 - Assignees: Apple Inc. - Applicants: Apple Inc. - Inventors: Ian M. Richter - Web page: https://patentgrep.com/patent/US12223943B2 ## CPC - G10L 13/00: Speech synthesis; Text to speech systems - G06T 11/00: Two-dimensional [2D] image generation - G10L 13/033: Voice editing, e.g. manipulating the voice of the synthesiser - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract Various implementations disclosed herein include devices, systems, and methods for synthesizing virtual speech. In various implementations, a device includes a display, an audio sensor, a non-transitory memory and one or more processors coupled with the non-transitory memory. A computer-generated reality (CGR) representation of a fictional character is displayed in a CGR environment on the display. A speech input is received from a first person via the audio sensor. The speech input is modified based on one or more language characteristic values associated with the fictional character in order to generate CGR speech. The CGR speech is outputted in the CGR environment via the CGR representation of the fictional character. ## Claims ### Claim 1 A method comprising: at a device including a display, an audio sensor, a non-transitory memory and one or more processors coupled with the non-transitory memory: presenting, via the display, a representation of an environment; and while presenting the representation of the environment, receiving, via the audio sensor, a speech input from a user of the device; determining whether or not a speech characteristic of the speech input from the user matches a target speech characteristic associated with the environment; in response to determining that the speech characteristic of the speech input from the user does not match the target speech characteristic associated with the environment, modifying the speech input from the user based on the target speech characteristic associated with the environment in order to generate a modified speech input with a modified speech characteristic that matches the target speech characteristic associated with the environment; and outputting the modified speech input in the representation of the environment. ### Claim 2 (depends on 1) The method of claim 1, wherein modifying the speech input comprises modifying an intonation associated with the speech input to generate the modified speech input with a modified intonation associated with the target speech characteristic. ### Claim 3 (depends on 1) The method of claim 1, wherein modifying the speech input comprises modifying a talking speed associated with the speech input to generate the modified speech input with a modified talking speed associated with the target speech characteristic. ### Claim 4 (depends on 1) The method of claim 1, wherein modifying the speech input comprises modifying a set of phrases included in the speech input to generate the modified speech input with a modified set of phrases associated with the target speech characteristic. ### Claim 5 (depends on 1) The method of claim 1, wherein modifying the speech input comprises modifying an accent associated with the speech input to generate the modified speech input with a modified accent associated with the target speech characteristic. ### Claim 6 (depends on 1) The method of claim 1, further comprising displaying, on the display, an indication that the speech input has been modified to match the target speech characteristic. ### Claim 7 (depends on 1) The method of claim 1, wherein the target speech characteristic indicates a geographical location; and wherein modifying the speech input comprises modifying the speech input such that the modified speech input matches a speaking style of the location. ### Claim 8 (depends on 1) The method of claim 1, wherein the environment includes a person and the target speech characteristic is associated with the person. ### Claim 9 A device comprising: one or more processors; a display; an audio sensor; a non-transitory memory; and one or more programs stored in the non-transitory memory, which, when executed by the one or more processors, cause the device to: present, via the display, a representation of an environment; and while presenting the representation of the environment, receive, via the audio sensor, a speech input from a user of the device; determine whether or not a speech characteristic of the speech input from the user matches a target speech characteristic associated with the environment; in response to determining that the speech characteristic of the speech input from the user does not match the target speech characteristic associated with the environment, modify the speech input from the user based on the target speech characteristic associated with the environment in order to generate a modified speech input with a modified speech characteristic that matches the target speech characteristic associated with the environment; and output the modified speech input in the representation of the environment. ### Claim 10 (depends on 9) The device of claim 9, wherein modifying the speech input comprises modifying an intonation associated with the speech input to generate the modified speech input with a modified intonation associated with the target speech characteristic. ### Claim 11 (depends on 9) The device of claim 9, wherein modifying the speech input comprises modifying a talking speed associated with the speech input to generate the modified speech input with a modified talking speed associated with the target speech characteristic. ### Claim 12 (depends on 9) The device of claim 9, wherein modifying the speech input comprises modifying a set of phrases included in the speech input to generate the modified speech input with a modified set of phrases associated with the target speech characteristic. ### Claim 13 (depends on 9) The device of claim 9, wherein modifying the speech input comprises modifying an accent associated with the speech input to generate the modified speech input with a modified accent associated with the target speech characteristic. ### Claim 14 (depends on 9) The device of claim 9, further comprising displaying, on the display, an indication that the speech input has been modified to match the target speech characteristic. ### Claim 15 (depends on 9) The device of claim 9, wherein the target speech characteristic indicates a geographical location; and wherein modifying the speech input comprises modifying the speech input such that the modified speech input matches a speaking style of the location. ### Claim 16 (depends on 9) The device of claim 9, wherein the environment includes a person and the target speech characteristic is associated with the person. ### Claim 17 A non-transitory memory storing one or more programs, which, when executed by one or more processors of a device including a display and an audio sensor, cause the device to: present, via the display, a representation of an environment; and while presenting the representation of the environment, receive, via the audio sensor, a speech input from a user of the device; determine whether or not a speech characteristic of the speech input from the user matches a target speech characteristic associated with the environment; in response to determining that the speech characteristic of the speech input from the user does not match the target speech characteristic associated with the environment, modify the speech input from the user based on the target speech characteristic associated with the environment in order to generate a modified speech input with a modified speech characteristic that matches the target speech characteristic associated with the environment; and output the modified speech input in the representation of the environment. ### Claim 18 (depends on 17) The non-transitory memory of claim 17, wherein modifying the speech input comprises modifying an intonation associated with the speech input to generate the modified speech input with a modified intonation associated with the target speech characteristic. ### Claim 19 (depends on 17) The non-transitory memory of claim 17, wherein modifying the speech input comprises modifying a talking speed associated with the speech input to generate the modified speech input with a modified talking speed associated with the target speech characteristic. ### Claim 20 (depends on 17) The non-transitory memory of claim 17, wherein modifying the speech input comprises modifying a set of phrases included in the speech input to generate the modified speech input with a modified set of phrases associated with the target speech characteristic.