# US 11,908,488 B2 · Assessing reading ability through grapheme-phoneme correspondence analysis > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,908,488 B2 - Document ID: US11908488B2 - Status: Granted - Kind: B2 - Application number: 17/333,808 - Filed: 2021-05-28 - Published: 2022-12-01 - Granted: 2024-02-20 - Earliest claimed: 2021-05-28 - Assignees: Metametrics, Inc. - Applicants: Metametrics, Inc. - Inventors: Neena Marie Saha - Web page: https://patentgrep.com/patent/US11908488B2 ## CPC - G09B 19/04: Speaking (with audible presentation of the material to be studied G09B5/04) - G10L 25/51: for comparison or discrimination - G09B 17/003: {electrically operated apparatus or devices} - G10L 15/02: Feature extraction for speech recognition; Selection of recognition unit - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - G10L 2015/025: {Phonemes, fenemes or fenones being the recognition units} - 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 A computing device translates a spoken word into a corresponding ordered set of spoken phonemes and analyzes correctness of the spoken word relative to a target word. The analyzing includes attempting to locate each of the spoken phonemes in an ordered set of grapheme-phoneme correspondences (GPCs) describing the target word, and determining whether or not the ordered set of spoken phonemes comprises a same number of phonemes as in the ordered set of GPCs. The analyzing also includes comparing the order of the ordered set of spoken phonemes against the order of the ordered set of GPCs. The computing device generates a report, based on the analyzing, that identifies at least one of the GPCs in the ordered set of GPCs as having been incorrectly applied in decoding the target word. ## Claims ### Claim 1 A method of providing a technical solution to the technical problem of providing granular assessment of grapheme-phoneme correspondence (GPC) correctness, when assessing reading ability, by comparing phonemes of a spoken word to phonemes corresponding to the graphemes of a displayed target word, implemented by a computing device, the method comprising: in a database, storing a plurality of target words for decoding by a student; for each target word, storing at least one ordered set of grapheme-phoneme correspondences (GPCs) that fully describe such word; designating a particular target word, of the plurality of target words, for display to a student in conjunction with a prompt for the student to decode and speak the designated target word; obtaining audio corresponding to a spoken word, the spoken word representing a student's attempt to decode and speak the designated target word correctly; via a specialized speech-to-text engine, converting the audio corresponding to the spoken word into a corresponding ordered set of spoken phonemes; analyzing correctness of the phonemes of the spoken word relative to the phonemes corresponding to the graphemes of the designated target word, the analyzing comprising: attempting to locate each of the spoken phonemes, from the obtained audio, in the ordered set of grapheme-phoneme correspondences (GPCs) describing the designated target word; determining whether or not the ordered set of spoken phonemes comprises a same number of phonemes as in the ordered set of GPCs; and comparing the order of the ordered set of spoken phonemes against the order of the ordered set of GPCs; and generating a report, based on the analyzing, that identifies at least one of the GPCs in the ordered set of GPCs as having been incorrectly applied in decoding the designated target word. ### Claim 2 (depends on 1) The method of claim 1, further comprising: failing to locate, in the ordered set of GPCs, an incorrectly spoken phoneme in the ordered set of spoken phonemes; wherein generating the report comprises, in response to failing to locate the incorrectly spoken phoneme, identifying the incorrectly spoken phoneme in the report. ### Claim 3 (depends on 1) The method of claim 1, wherein the analyzing further comprises identifying, as one of the incorrectly applied GPCs, a GPC in the ordered set of GPCs that comprises a phoneme not included in the ordered set of spoken phonemes. ### Claim 4 (depends on 1) The method of claim 1, wherein generating the report comprises including, in the report, a phoneme selection correctness score computed based on an extent to which the spoken phonemes are located in the ordered set of GPCs. ### Claim 5 (depends on 1) The method of claim 1, wherein generating the report comprises including, in the report, a grapheme selection correctness score computed based on an extent to which the spoken phonemes are phonetically valid pronunciations of the graphemes in the ordered set of GPCs. ### Claim 6 (depends on 1) The method of claim 1, wherein generating the report comprises including, in the report, a positional correctness score computed based on an extent to which the spoken phonemes are ordered in accordance with the ordered set of GPCs. ### Claim 7 (depends on 1) The method of claim 1, wherein generating the report comprises including, in the report, an auditory similarity score computed based on how phonetically close the spoken phonemes are to the phonemes in the ordered set of GPCs. ### Claim 8 (depends on 1) The method of claim 1, wherein converting the audio corresponding to the spoken word into the corresponding ordered set of spoken phonemes comprises processing received audio comprising the spoken word using a speech-to-text engine to obtain text corresponding to the word, and converting the text into the ordered set of spoken phonemes. ### Claim 9 (depends on 1) The method of claim 1, wherein converting the audio corresponding to the spoken word into the corresponding ordered set of spoken phonemes comprises identifying each of the spoken phonemes in received audio comprising the spoken word without processing the spoken word into corresponding text first. ### Claim 10 (depends on 1) The method of claim 1, wherein the step of converting audio corresponding to the spoken word into a corresponding ordered set of spoken phonemes is carried out by a speech-to-text engine that specifically outputs spoken phonemes rather than processing the spoken phonemes, assessing similarity of the spoken phonemes to known words, identifying a most-likely intended word based on the processing and assessing steps, and outputting the most-likely intended word. ### Claim 11 (depends on 1) The method of claim 1, wherein obtaining audio corresponding to the spoken word includes receiving the spoken word directly from the student via a microphone. ### Claim 12 (depends on 1) The method of claim 1, wherein obtaining audio corresponding to the spoken word includes receiving a recording of the spoken word from a remote device. ### Claim 13 (depends on 12) The method of claim 12, wherein receiving the recording of the spoken word from the remote device includes receiving a media stream comprising the spoken word over a network. ### Claim 14 (depends on 12) The method of claim 12, wherein receiving the recording of the spoken word from the remote device includes receiving a file comprising the spoken word. ### Claim 15 (depends on 14) The method of claim 14, wherein receiving the file comprising the spoken word includes receiving the file via network download, email, installed memory device, or Multimedia Messaging Service (MMS) message attachment. ### Claim 16 (depends on 1) The method of claim 1, wherein: the method further comprises failing to locate at least one of the spoken phonemes, from the obtained audio, in the ordered set of GPCs describing the designated target word, each unlocated spoken phoneme defining an incorrectly spoken phoneme; and generating the report comprises identifying the at least one incorrectly spoken phoneme in the report. ### Claim 17 A method of providing a technical solution to the technical problem of providing granular assessment of grapheme-phoneme correspondence (GPC) correctness, when assessing reading ability, by comparing phonemes of a spoken word to phonemes corresponding to the graphemes of a displayed target word, implemented by a computing device, the method comprising: in a database, storing a plurality of target words for decoding by a student; for each target word, storing at least one ordered set of grapheme-phoneme correspondences (GPCs) that fully describe such word; designating a particular target word, of the plurality of target words, for display to a student in conjunction with a prompt for the student to decode and speak the designated target word; obtaining audio corresponding to a spoken word, the spoken word representing a student's attempt to decode and speak the designated target word correctly; via a specialized speech-to-text engine, converting audio corresponding to the spoken word into a corresponding ordered set of spoken phonemes; analyzing correctness of the phonemes of the spoken word relative to the phonemes corresponding to the graphemes of the designated target word, the analyzing comprising: attempting to locate, in the obtained audio, each of the phonemes from the ordered set of grapheme-phoneme correspondences (GPCs) describing the designated target word; determining whether or not the ordered set of spoken phonemes comprises a same number of phonemes as in the ordered set of GPCs; and comparing the order of the ordered set of spoken phonemes against the order of the ordered set of GPCs; and generating a report, based on the analyzing, that identifies at least one of the GPCs in the ordered set of GPCs as having been incorrectly applied in decoding the designated target word. ### Claim 18 (depends on 17) The method of claim 17, wherein: the method further comprises failing to locate at least one of the target phonemes, from the ordered set of GPCs describing the designated target word, in the obtained audio, each unlocated target phoneme defining an incorrectly spoken phoneme; and generating the report comprises identifying the at least one incorrectly spoken phoneme in the report. ### Claim 19 A method of providing a technical solution to the technical problem of providing granular assessment of grapheme-phoneme correspondence (GPC) correctness, when assessing reading ability, by comparing phonemes of a spoken word to phonemes corresponding to the graphemes of a displayed target word, implemented by a computing device, the method comprising: in a database, storing a plurality of target words for decoding by a student; in the database, storing at least one ordered set of grapheme-phoneme correspondences (GPCs) that fully describe such word; displaying a particular target word, of the plurality of target words, to a student in conjunction with a prompt for the student to decode and speak the designated target word; obtaining audio corresponding to a spoken word, the spoken word representing a student's attempt to decode and speak the designated target word correctly; via a specialized speech-to-text engine, converting the audio corresponding to the spoken word into a corresponding ordered set of spoken phonemes; analyzing correctness of the phonemes of the spoken word relative to the phonemes corresponding to the graphemes of the designated target word, the analyzing comprising: attempting to locate 1) each of the spoken phonemes, from the obtained audio, in the ordered set of grapheme-phoneme correspondences (GPCs) describing the designated target word, 2) in the obtained audio, each of the phonemes from the ordered set of grapheme-phoneme correspondences (GPCs) describing the designated target word, or 3) both; determining whether or not the ordered set of spoken phonemes comprises a same number of phonemes as in the ordered set of GPCs; and comparing the order of the ordered set of spoken phonemes against the order of the ordered set of GPCs; and generating a report, based on the analyzing, that identifies at least one of the GPCs in the ordered set of GPCs as having been incorrectly applied in decoding the designated target word. ### Claim 20 (depends on 19) The method of claim 19, wherein the steps of displaying, obtaining, converting, and analyzing are carried out for each of the plurality of target words, and wherein generating a report includes generating a report that identifies all of the incorrectly applied GPCs from the analyzing steps carried out for all of the respective target words.