# US 2015/0149172 A1 · Word cloud audio navigation

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

- Number: US 2015/0149172 A1
- Document ID: US20150149172A1
- Status: Published application
- Kind: A1
- Application number: 14/610,798
- Filed: 2015-01-30
- Published: 2015-05-28
- Earliest claimed: 2009-08-17
- Assignees: Avaya Inc.
- Applicants: Avaya Inc.
- Inventors: Michael Doyle; Thomas Greenwood
- Web page: https://patentgrep.com/patent/US20150149172A1

## CPC

- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 15/08: Speech classification or search
- G10L 15/083: {Recognition networks (G10L15/142, G10L15/16 take precedence)}
- G10L 21/10: Transforming into visible information
- G10L 25/57: for processing of video signals
- G11B 27/322: {used signal is digitally coded}
- H04L 63/06: {for supporting key management in a packet data network (cryptographic mechanisms or cryptographic arrangements for key management H04L9/08)}
- H04L 63/30: {for supporting lawful interception, monitoring or retaining of communications or communication related information (circuit switched telephony call monitoring H04M3/2281)}
- H04L 65/1076: Screening of IP real time communications, e.g. spam over Internet telephony [SPIT]
- H04M 3/42221: {Conversation recording systems (at the subscriber's set H04M1/656)}
- H04N 7/141: {between two video terminals, e.g. videophone (telephonic communication systems combined with television receiver for reception of entertainment or information matter H04M11/085)}
- H04N 21/8586: {by using a URL (processing chained hypermedia data for information retrieval G06F16/94; information retrieval from the Internet by using URLs G06F16/955; URL in broadcast information H04H20/93; Web-based protocols H04L67/02)}
- G10L 2015/085: {Methods for reducing search complexity, pruning}
- H04M 2201/38: Displays
- H04M 2201/40: using speech recognition
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G11B: INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER (recording measured values in a way that does not require playback through a transducer G01D9/00; recording or playback apparatus using mechanically marked tape, e.g. punched paper tape, or using unit records, e.g. punched or magnetically marked cards G06K; transferring data from one type of record carrier to another G06K1/18; circuits for coupling output of reproducer to radio receiver H04B1/20; gramophone pick-ups or like acoustic electromechanical transducers or circuits therefor H04R)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

The present invention is directed generally to linking a collection of words and/or phrases with locations in a video and/or audio stream where the words and/or phrases occur and/or associations of a collection of words and/or phrases with a call history.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A method, comprising:
receiving, by a processor, at least one of an audio and video stream;
identifying, by a processor, occurrences of selected words and/or phrases in the stream;
creating, by a processor, a word cloud comprising at least some of the selected words and/or phrases in the stream, the word cloud indicating relative frequencies of use of each of the selected words and/or phrases in the stream; and
linking, by a processor, the words and/or phrases in the word cloud to timestamps and/or corresponding locations of each of the words and/or phrases in the audio and video stream.

### Claim 22 (depends on 21)

The method of claim 21, wherein the word cloud omits selected prepositions, adjectives, and/or adverbs in the stream and wherein the selected words and/or phrases are linked with timestamps, whereby user selection of a linked word and/or phrase allows the user to access directly the corresponding portion of the at least one of an audio and video stream containing the user selected word and/or phrase.

### Claim 23 (depends on 21)

The method of claim 21, wherein the words and/or phrases in the word cloud are hyperlinked to corresponding locations for each selected word and/or phrase, wherein, in the word cloud, at least one of a size, font type, font color, and location of a word and/or phrase is a function of a frequency of occurrence of the word and/or phrase in the stream.

### Claim 24 (depends on 22)

The method of claim 22, wherein the stream is a recorded live voice call and wherein the stream is indexed into a call history comprising dates and times of calls and call participants, wherein, using the results of the linking step, the locations of the identified words and/or phrases may be located via the timestamps without searching of the surrounding portions of the stream or a text equivalent thereof, and further comprising:
in response to a user selecting a word and/or phrase from the word cloud, providing the user with a portion of the stream associated with a timestamp linked to the selected word and/or phrase.

### Claim 25 (depends on 22)

The method of claim 22, wherein the at least one of an audio and video stream is a call, wherein the at least one audio and video stream comprises multiple audio and/or video streams, wherein each of the multiple audio and/or video streams corresponds to a different word cloud, wherein each of the word clouds is linked to or displayed adjacent to a corresponding callee/caller pairing, and further comprising:
in response to a user selecting a word and/or phrase from the word cloud, providing the user with a list of locations in the stream containing the selected word and/or phrase.

### Claim 26 (depends on 21)

The method of claim 21, further comprising:
receiving, by a processor, a user selection of a word and/or phrase in the word cloud;
displaying, by a processor, a list of times and/or locations in the at least one of an audio and video stream associated with the user selected word and/or phrase, each time and/or location being displayed with a portion of the corresponding text containing the user selected word and/or phrase;
receiving, by a processor, a user selection of a displayed time and/or location; and
providing, by a processor, the corresponding text at the user selected time and/or location.

### Claim 27 (depends on 21)

A tangible and non-transient computer readable medium encoded with processor executable instructions to perform the steps of claim 21.

### Claim 28

A device, comprising:
a computer operable to:
receive at least one of an audio and video stream;
identify occurrences of selected words and/or phrases in the stream;
create a word cloud comprising at least some of the selected words and/or phrases in the stream, the word cloud indicating relative frequencies of use of each of the selected words and/or phrases in the stream; and
link the words and/or phrases in the word cloud to timestamps and/or corresponding locations of each of the words and/or phrases in the audio and video stream.

### Claim 29 (depends on 28)

The device of claim 28, wherein the word cloud omits selected prepositions, adjectives, and/or adverbs in the stream and wherein the selected words and/or phrases are linked with timestamps, whereby user selection of a linked word and/or phrase allows the user to access directly the corresponding portion of the at least one of an audio and video stream containing the user selected word and/or phrase.

### Claim 30 (depends on 28)

The device of claim 28, wherein the words and/or phrases in the word cloud are hyperlinked to corresponding locations for each selected word and/or phrase, wherein, in the word cloud, at least one of a size, font type, font color, and location of a word and/or phrase is a function of a frequency of occurrence of the word and/or phrase in the stream.

### Claim 31 (depends on 29)

The device of claim 29, wherein the stream is a recorded live voice call and wherein the stream is indexed into a call history comprising dates and times of calls and call participants, wherein, using the results of the linking step, the locations of the identified words and/or phrases may be located via the timestamps without searching of the surrounding portions of the stream or a text equivalent thereof, and wherein, the computer, in response to a user selecting a word and/or phrase from the word cloud, provides the user with a portion of the stream associated with a timestamp linked to the selected word and/or phrase.

### Claim 32 (depends on 29)

The device of claim 29, wherein the at least one of an audio and video stream is a call, wherein the at least one audio and video stream comprises multiple audio and/or video streams, wherein each of the multiple audio and/or video streams corresponds to a different word cloud, wherein each of the word clouds is linked to or displayed adjacent to a corresponding callee/caller pairing, and wherein the computer, in response to a user selecting a word and/or phrase from the word cloud, provides the user with a list of locations in the stream containing the selected word and/or phrase.

### Claim 33 (depends on 28)

The device of claim 28, wherein the portion of the stream is selected such that subparts of the portion precede and follow the selected word and/or phrase, wherein the stream is a recorded live voice call, wherein the stream is indexed into a call history comprising dates and times of calls and call participants, wherein, using the results of the linking step, the locations of the identified words and/or phrases may be located via the timestamps without searching of the surrounding portions of the stream or a text equivalent thereof

### Claim 34 (depends on 28)

The device of claim 28, wherein the computer receives a user selection of a word and/or phrase in the word cloud; displays a list of times and/or locations in the at least one of an audio and video stream associated with the user selected word and/or phrase, each time and/or location being displayed with a portion of the corresponding text containing the user selected word and/or phrase; receives a user selection of a displayed time and/or location; and provides the corresponding text at the user selected time and/or location.

### Claim 35

A method, comprising:
providing, by a processor, a user with a word cloud, the word cloud containing a plurality of words and/or phrases linked to respective locations in an audio and/or video stream where each word and/or phrase occurs;
receiving, by the processor and from the user, a selected word and/or phrase; and
providing, by the processor, the user with at least one of (a) a list of locations in the stream where the selected word and/or phrase occurs and (b) a portion of the stream containing the selected word and/or phrase;
receiving, by the processor, a user selection of a displayed at least one of (a) a list of locations in the stream where the selected word and/or phrase occurs and (b) a portion of the stream containing the selected word and/or phrase; and
providing, by the processor, the corresponding text at the user selected at least one of (a) a list of locations in the stream where the selected word and/or phrase occurs and (b) a portion of the stream containing the selected word and/or phrase.

### Claim 36 (depends on 35)

The method of claim 35, wherein, in the word cloud, at least one of a size, font type, font color, and location of a word and/or phrase is a function of a frequency of occurrence of the word and/or phrase in the stream.

### Claim 37 (depends on 35)

The method of claim 35, wherein the user is provided with (a).

### Claim 38 (depends on 35)

The method of claim 35, wherein the user is provided with (b).

### Claim 39 (depends on 35)

The method of claim 35, wherein the stream is a recorded live voice call and wherein the stream is indexed into a call history comprising dates and times of calls and call participants, wherein, using the results of the linking step, the locations of the identified words and/or phrases may be located via the timestamps without searching of the surrounding portions of the stream or a text equivalent thereof.

### Claim 40 (depends on 35)

A tangible and non-transient computer readable medium encoded with processor executable instructions to perform the steps of claim 35.
