# US 2014/0234811 A1 · Systems and methods for learning using contextual feedback

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2014/0234811 A1
- Document ID: US20140234811A1
- Status: Published application
- Kind: A1
- Application number: 14/263,931
- Filed: 2014-04-28
- Published: 2014-08-21
- Earliest claimed: 2004-09-16
- Assignees: LENA Foundation
- Applicants: LENA Foundation
- Inventors: Terrance D. Paul
- Web page: https://patentgrep.com/patent/US20140234811A1

## CPC

- G09B 5/04: with audible presentation of the material to be studied (sound recording or reproducing G11B)
- G09B 5/00: Electrically-operated educational appliances (working with questions and answers G09B7/00; simulators G09B9/00; advertising or displaying in general G09F)
- G10L 17/26: Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
- 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 method of supporting vocabulary and language learning by positioning at least one microphone so as to capture speech in the listening environment of a learner. The microphone is monitored to develop a speech signal. The speech signal is analyzed to determine at least one characteristic of the speech or vocalization, wherein the characteristic indicates a qualitative or quantitative feature of the speech. The determined characteristic is compared to a preselected standard or such characteristic is tracked to show growth over time and the comparison or growth is reported to the person associated with the speech signal or person who potentially can affect the language environment of the learner.

## Claims

### Claim at position 1

1-47. (canceled)

### Claim 48

A system for supporting language acquisition, the system comprising:
a sound capture component operable to capture sounds produced by a first person and a plurality of other sound sources, wherein the plurality of other sound sources includes other people;
a sound processor coupled to the sound capture component and operable to analyze a sound signal from the sound capture component and identify characteristics of the captured sounds; and
a reporting component coupled to the sound processor and operable to report metrics that quantify the characteristics of the captured sounds, wherein the characteristics of the captured sounds include speaker identification of portions of the captured sounds.

### Claim 49 (depends on 48)

The system of claim 48 wherein the sound capture component is substantially fixed in relation to the first person.

### Claim 50 (depends on 49)

The system of claim 49, wherein the sound capture component is housed in a garment of the first person.

### Claim 51 (depends on 50)

The system of claim 50, wherein the worn nature of the sound capture component improves sound capture and assists in distinguishing sounds uttered by the first person and the plurality of other sound sources.

### Claim 52 (depends on 48)

The system of claim 48 wherein the reporting component logs metrics for review at a time after the sound is captured.

### Claim 53 (depends on 48)

The system of claim 48 wherein the system is adapted to support pre-linguistic language acquisition.

### Claim 54

A system for assessing the language development of children and adults, the system comprising:
a speech capture component operable to capture vocalizations and utterances of people in natural settings, including a patient;
a speech processor coupled to the speech capture component and operable to analyze the captured vocalizations and utterances and identifying characteristics of the captured vocalizations and utterances, including those of the patient; and
a reporting component coupled to the speech processor and operable to report metrics that quantify the identified characteristics and compare the identified characteristics associated with the patient to normative charts to detect and diagnose various conditions.

### Claim 55 (depends on 54)

The system of claim 54, wherein the normative charts are previously developed by capturing and processing previous vocalizations and utterances of people to generate the normative charts.

### Claim 56 (depends on 54)

The system of claim 54 wherein the speech capture component comprises a wearable sound capture device.

### Claim 57 (depends on 54)

The system of claim 54 wherein the speech capture component and speech processor are integrated as a single device.

### Claim 58 (depends on 54)

The system of claim 54 wherein the speech processor comprises mechanisms operable to count the occurrence of words in the vocalizations and utterances.

### Claim 59 (depends on 54)

The system of claim 54 wherein the speech processor comprises mechanisms operable to estimate the length of words in the communications.

### Claim 60 (depends on 54)

The system of claim 54 wherein the speech processor comprises mechanisms operable to measure the complexity of the communications.

### Claim 61 (depends on 54)

The system of claim 54 wherein the speech processor comprises mechanisms operable to estimate emotional content of the communications.

### Claim 62

A method of supporting language development comprising:
capturing sound in a natural language environment, using at least one sound capture device which is located in the natural language environment;
developing a sound signal from the captured sound, wherein the sound signal comprises components representing one or more features that affect a language development environment;
analyzing the sound signal to determine at least one characteristic of the language development environment, wherein at least one characteristic indicates a qualitative or quantitative assessment of the one or more features, wherein the at least one characteristic include speaker identification of portions of the captured sounds;
comparing the determined characteristic to a preselected standard or change over time; and
reporting results.

### Claim 63 (depends on 62)

The method of claim 62 further comprising positioning at least one sound recording device in a substantially fixed location relative to a person.

### Claim 64 (depends on 63)

The method of claim 63 wherein the act of positioning at least one sound recording device comprises placing the sound recording device within an article of clothing of the person.

### Claim 65 (depends on 64)

The method of claim 64 wherein the positioning of the at least one sound recording device improves sound capture and assists in distinguishing sounds uttered by the first person and the plurality of other sound sources.

### Claim 66 (depends on 62)

The method of claim 62, wherein the at least one characteristic is a frequency and duration of conversational turn-taking

### Claim 67 (depends on 62)

The method of claim 62 wherein the sound captured includes human made sound, wherein the human made sound may include a number of utterances, and wherein the utterances include cooing, babbling, prelinguistic sounds and linguistic sounds.

### Claim 68 (depends on 62)

The method of claim 62 wherein the speech involves at least two participants and the method further comprises associating the sound signal with a particular one of the at least two participants.
