# US 11,307,825 B1 · Recording a separated sound from a sound stream mixture on a personal device

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

- Number: US 11,307,825 B1
- Document ID: US11307825B1
- Status: Granted
- Kind: B1
- Application number: 17/187,868
- Filed: 2021-02-28
- Granted: 2022-04-19
- Earliest claimed: 2021-02-28
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Sarbajit K. Rakshit; Manish Anand Bhide; Seema Nagar; Madhavi Katari; Kuntal Dey
- Web page: https://patentgrep.com/patent/US11307825B1

## CPC

- G06F 3/165: {Management of the audio stream, e.g. setting of volume, audio stream path}
- G06F 3/04817: using icons (graphical or visual programming using iconic symbols G06F8/34)
- G06F 3/0484: for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G10L 21/10: Transforming into visible information
- G10L 25/51: for comparison or discrimination
- G02B 27/017: {Head mounted}
- G10L 21/003: Changing voice quality, e.g. pitch or formants
- G10L 21/0272: Voice signal separating
- G10L 25/30: using neural networks
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G02B: OPTICAL ELEMENTS, SYSTEMS OR APPARATUS

## Abstract

The method provides for one or more processor receiving on a personal device, a mixture of sounds within a sound stream from multiple sources. The one or more processors identifying one or more sounds of the mixture of sounds from the multiple sources, based on a sound separation technique. The one or more processors displaying on a user interface of the personal device an icon corresponding respectively to a classification of the one or more sounds identified from the multiple sources. The one or more processors receiving a selection of a sound from the mixture of the multiple sounds, based on an action by a user of the personal device selecting the icon displayed on the user interface of the personal device, and the one or more processors recording the sound from the mixture of the multiple sounds selected by the user.

## Claims

### Claim 1

A method for selectively recording one or more sounds from a multiple-sound environment, the method comprising:
receiving, by one or more processors, a mixture of sounds from multiple sources;
performing, by the one or more processors, a separation of the mixture of sounds by applying one or more sound separation techniques;
identifying, by the one or more processors, one or more sounds of the mixture of sounds from the multiple sources, based on training using machine learning techniques;
generating, by the one or more processors, a set of icons corresponding respectively to a classification assigned to respective identified sounds of the mixture of sounds from the multiple sources;
receiving, by the one or more processors, a selection of a first icon of the generated set of icons associated with the sound, based on an action by a user selecting the first icon; and
recording, by the one or more processors, the sound from the mixture of sounds from the multiple sources associated with the first icon selected by the user.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
receiving, by the one or more processors, the mixture of sounds utilizing two or more microphones; and
displaying, by the one or more processors, the set of icons on a user interface of a personal device of the user, wherein the personal device of the user is augmented reality (AR) glasses configured to record and store recorded sounds.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
receiving, by the one or more processors, the mixture of sounds utilizing two or more microphones; and
displaying, by the one or more processors, the set of icons on a user interface of a personal device of the user, wherein the personal device of the user is a smart device configured to record and store recorded sounds.

### Claim 4 (depends on 1)

The method of claim 1, wherein a set of parameters associated with recording the sound from the mixture of sounds selected by the action of the user selecting the first icon of the displayed set of icons associated with the mixture of sounds, are controlled by the user selecting displayed options.

### Claim 5 (depends on 1)

The method of claim 1, wherein an icon of the set of icons corresponds to a category classification.

### Claim 6 (depends on 1)

The method of claim 1, wherein the user alters a property of the sound from the mixture of sounds while recording the sound, and wherein the property of the sound includes attributes of volume, sound pitch, and speed of recording.

### Claim 7 (depends on 1)

The method of claim 1, wherein the machine learning techniques include supervised learning in which a plurality of distinct audio sounds is delivered along with identification of the distinct audio sounds.

### Claim 8

A computer program product for selectively recording one or more sounds from a multiple-sound environment, the computer program product comprising:
one or more computer-readable storage media, and program instructions stored on the one or more computer-readable storage media, the program instructions comprising:
program instructions to receive mixture of sounds from multiple sources;
program instructions to perform a separation of the mixture of sounds by applying one or more sound separation techniques;
program instructions to identify one or more sounds of the mixture of sounds from the multiple sources, based on training using machine learning techniques;
program instructions to generate a set of icons corresponding respectively to a classification assigned to respective identified sounds of the mixture of sounds from the multiple sources;
program instructions to receive a selection of a first icon of the generated set of icons associated with the sound, based on an action by a user selecting the first icon; and
program instructions to record the sound from the mixture of sounds from the multiple sources associated with the first icon selected by the user.

### Claim 9 (depends on 8)

The computer program product of claim 8, further comprising:
program instructions to receive the mixture of sounds by two or more microphones; and
program instructions to display the set of icons on a user interface of a personal device of the user, wherein the personal device of the user is augmented reality (AR) glasses configured to record and store recorded sounds.

### Claim 10 (depends on 8)

The computer program product of claim 8, further comprising:
program instructions to receive the mixture of sounds by two or more microphones; and
program instructions to display the set of icons on a user interface of a personal device of the user, wherein the personal device of the user is a smart device configured to record and store recorded sounds.

### Claim 11 (depends on 8)

The computer program product of claim 8, wherein a set of parameters associated with recording the sound from the mixture of sounds selected by the action of the user selecting the first icon of the displayed set of icons associated with the mixture of sounds, are controlled by the user selecting displayed options.

### Claim 12 (depends on 8)

The computer program product of claim 8, wherein the user alters a property of the sound from the mixture of sounds while recording the sound, and wherein the property of the sound includes attributes of volume, sound pitch, and speed of recording.

### Claim 13 (depends on 8)

The computer program product of claim 8, wherein the machine learning techniques include supervised learning in which a plurality of distinct audio sounds is delivered along with identification of the distinct audio sounds.

### Claim 14

A computer system for selectively recording one or more sounds from a multiple-sound environment, the computer system comprising:
one or more computer processors;
one or more computer-readable storage media, and program instructions stored on the one or more computer-readable storage media, the program instructions comprising:
program instructions to receive mixture of sounds from multiple sources;
program instructions to perform a separation of the mixture of sounds by applying one or more sound separation techniques;
program instructions to identify one or more sounds of the mixture of sounds from the multiple sources, based on training using machine learning techniques;
program instructions to generate a set of icons corresponding respectively to a classification assigned to respective identified sounds of the mixture of sounds from the multiple sources;
program instructions to receive a selection of a first icon of the generated set of icons associated with the sound, based on an action by a user selecting the first icon; and
program instructions to record the sound from the mixture of sounds from the multiple sources associated with the first icon selected by the user.

### Claim 15 (depends on 14)

The computer system of claim 14, further comprising:
program instructions to receive the mixture of sounds by two or more microphones; and
program instructions to display the set of icons on a user interface of a personal device of the user, wherein the personal device of the user is augmented reality (AR) glasses configured to record and store recorded sounds.

### Claim 16 (depends on 14)

The computer system of claim 14, further comprising:
program instructions to receive the mixture of sounds by two or more microphones; and
program instructions to display the set of icons on a user interface of a personal device of the user, wherein the personal device of the user is a smart device configured to record and store recorded sounds.

### Claim 17 (depends on 14)

The computer system of claim 14, wherein a set of parameters associated with recording the sound from the mixture of sounds selected by the action of the user selecting the first icon of the displayed set of icons associated with the mixture of sounds, are controlled by the user selecting displayed options.

### Claim 18 (depends on 14)

The computer system of claim 14, wherein an icon of the set of icons corresponds to a category classification.

### Claim 19 (depends on 14)

The computer system of claim 14, wherein program instructions altering a property of the sound from the mixture of sounds while recording the sound is based on program instructions of a selected option received from the user, and wherein the property of the sound includes attributes of volume, sound pitch, and speed of recording.

### Claim 20 (depends on 14)

The computer system of claim 14, wherein the program instructions to identify the one or more sounds based on training using machine learning techniques includes programming instructions to:
apply machine learning techniques that include supervised learning in which a plurality of distinct audio sounds is delivered along with identification of the distinct audio sounds.