# US 2021/0279276 A1 · Method and system for providing audio content

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

- Number: US 2021/0279276 A1
- Document ID: US20210279276A1
- Status: Published application
- Kind: A1
- Application number: 17/327,878
- Filed: 2021-05-24
- Published: 2021-09-09
- Earliest claimed: 2016-01-28
- Assignees: SubPLY Solutions Ltd.
- Applicants: SubPLY Solutions Ltd.
- Inventors: Gal KLEIN; Rachel LUDMER
- Web page: https://patentgrep.com/patent/US20210279276A1

## CPC

- G06F 16/685: {using automatically derived transcript of audio data, e.g. lyrics (speech recognition G10L15/00)}
- G06F 16/433: {using audio data}
- G06F 16/632: Query formulation
- G10L 17/18: Artificial neural networks; Connectionist approaches
- H04L 67/02: based on web technology, e.g. hypertext transfer protocol [HTTP]
- 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
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Methods and systems are disclosed in which audio broadcasts are converted into audio segments, for example, based on segment content. These audio segments are indexed, so as to be searchable, as computer searchable segments, for example, by network search engines and other computerized search tools.

## Claims

### Claim 1

A computer-implemented method for providing audio content in segments comprising:
obtaining an audio stream;
converting the audio stream to text;
separating the text into text segments based on at least one indicator; and, correlating each text segment with a corresponding portion of the audio from the audio stream, the corresponding portion of the audio defining an audio segment.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, additionally comprising:
enriching each audio segment such that each audio segment is a computer searchable audio segment.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, performed automatically by at least one processor.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein the at least one indicator is selected from at least one of: rules and policies, changes in the relatedness of words based on their meaning in a portion of the text, keywords, word markers, audio cues, and scores for relatedness between words in a portion of the text.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, wherein the at least one indicator includes a plurality of indicators.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the audio segments include segments of audio content based on at least one of topics, advertisements, and public service announcements.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the audio stream is from a broadcast.

### Claim 8 (depends on 4)

The computer-implemented method of claim 4, wherein the broadcast is selected from the group consisting of a radio broadcast, a television broadcast, a cable broadcast, a webcast, a podcast, and a network carried broadcast.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein the converting the audio stream to text is performed by at least one of automatic speech recognition software, hardware or combinations thereof.

### Claim 10 (depends on 2)

The computer-implemented method of claim 2, where the enrichment includes associating metadata, tags, images, and indexing items with said each audio segment.

### Claim 11

A system for providing audio content in segments comprising:
a computerized processing unit; and,
storage media for storing computer components for in communication with the computerized processing unit, the computer components comprising:
a first component for obtaining an audio stream;
a second component for converting the audio stream to text;
a third component for automatically separating the text into segments based on at least one indicator; and,
a fourth component for correlating each text segment with a corresponding portion of the audio from the audio stream, the corresponding portion of the audio defining an audio segment.

### Claim 12 (depends on 11)

The system of claim 11, additionally comprising:
a fifth component for enriching each audio segment such that each audio segment is a computer searchable audio segment.

### Claim 13 (depends on 11)

The system of claim 11, wherein the first component is configured for obtaining the audio stream from a broadcast, the broadcast selected from the group consisting of a radio broadcast, a television broadcast, a podcast, a network carried broadcast.

### Claim 14 (depends on 11)

The system of claim 11, wherein the third component separates the text into segments based on at least one indicator, the at least one indicator being applied to produce content based audio segments.

### Claim 15 (depends on 14)

The system of claim 14, wherein the content based audio segments include topics, and the third component selects topics by analyzing electronic documents including web pages.

### Claim 16 (depends on 11)

The system of claim 11, wherein the computerized processing unit includes a central processing unit and a graphics processing unit.

### Claim 17 (depends on 11)

The system of claim 11, wherein the second component for converting the audio stream to text is performed by an automatic speech recognition (ASR) module which executes on the graphics processing unit.

### Claim 18

A system for providing audio content in segments comprising:
a computerized processing unit, programmed to:
obtain an audio stream; and,
correlate text segments with the corresponding audio from the audio stream to produce audio segments;
a converter for converting the speech of the audio stream into text output, the converter in communication with the computerized processing unit; and,
a segmenter for automatically separating the text output into segments based on at least one indicator.

### Claim 19 (depends on 18)

The system of claim 18, wherein the converter includes an automatic speech recognition (ASR) module.

### Claim 20 (depends on 19)

The system of claim 19, wherein the computerized processing unit includes a central processing unit and a graphics processing unit and the ASR module executes on the graphics processing unit.
