# US 2025/0095686 A1 · Personalized adaptive meeting playback

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

- Number: US 2025/0095686 A1
- Document ID: US20250095686A1
- Status: Published application
- Kind: A1
- Application number: 18/965,797
- Filed: 2024-12-02
- Published: 2025-03-20
- Earliest claimed: 2022-09-12
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Adi L. MILLER; Haim SOMECH; Oded NAHIR
- Web page: https://patentgrep.com/patent/US20250095686A1

## CPC

- G11B 27/005: {Reproducing at a different information rate from the information rate of recording (for television signals H04N5/783)}
- G11B 27/34: Indicating arrangements {(indicating means incorporated in magazine or cassette G11B23/046 and G11B23/0875; indicating measured values in general G01D)}
- G11B 27/28: by using information signals recorded by the same method as the main recording {(G11B27/22 takes precedence)}
- H04L 12/1831: {Tracking arrangements for later retrieval, e.g. recording contents, participants activities or behavior, network status}
- H04N 7/155: {involving storage of or access to video conference sessions (tracking arrangements for later retrieval of a computer conference content or participants activities H04L12/1831)}
- G10L 21/043: by changing speed
- G10L 25/78: Detection of presence or absence of voice signals (switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10)
- 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)
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Technology is disclosed for programmatically determining, for a segment of a meeting recording, a user-specific adaptive playback speed, and generating a time-stretched segment playable at the adaptive playback speed. The adaptive playback speed is faster or slower than a default playback speed of the meeting recording. To determine the adaptive playback speed, this disclosure provides technologies to determine a playback data feature based on user-meeting data. The adaptive playback is generated based on the playback data feature. The segment is time-stretched to the adaptive playback speed to generate an updated meeting recording including the segment that is time-stretched and playable at the adaptive playback speed. In this manner, an updated meeting recording, specific to a user, and playable at an adaptive playback speed based on user-meeting data may reduce bandwidth associated with user's manually editing videos or rewinding playback, while improving user experience.

## Claims

### Claim 1

A computerized method, comprising:
accessing user-meeting data associated with a meeting recording playable at a default playback speed;
programmatically determining, for a respective segment of the meeting recording, at least one playback data feature based on the user-meeting data;
automatically classifying the respective segment of the meeting recording into a category based at least on the at least one playback data feature;
determining a ratio between a first word count of a prior segment and a second word count of the respective segment;
based at least in part on the category and the ratio, automatically determining, for the respective segment of the meeting recording, an adaptive playback speed that is faster or slower than the default playback speed;
time-stretching the respective segment of the meeting recording into a time-stretched segment based on the adaptive playback speed;
causing at least a portion of the meeting recording to be provided with the time-stretched segment; and
generating a data file comprising an updated meeting recording comprising the time-stretched segment.

### Claim 2 (depends on 1)

The computerized method of claim 1, wherein time-stretching the respective segment further comprises applying the ratio to the respective segment so that the first word count and the second word count are substantially equal per the period of time.

### Claim 3 (depends on 1)

The computerized method of claim 1, further comprising determining that the first word count, per period of time, differs from the second word count, per the period of time, wherein the adaptive playback speed is further determined based on the difference in the first word count and the second word count, per the period of time.

### Claim 4 (depends on 1)

The computerized method of claim 1, wherein each weight defines a corresponding adaptive playback speed to which a corresponding segment of a plurality of segments is time-stretched, wherein the updated meeting recording is playable at a plurality of playback speeds corresponding to the plurality of segments, at least two of the plurality of playback speeds being different from each other.

### Claim 5 (depends on 1)

The computerized method of claim 1, wherein the adaptive playback speed is further determined based on visual content associated with the meeting recording, wherein the respective segment of the meeting recording is time-stretched to coordinate audio of the meeting recording with the visual content.

### Claim 6 (depends on 1)

The computerized method of claim 1, further comprising determining at least one of the respective segment or the prior segment of the meeting recording by:
determining a contiguous portion of the meeting recording having a common playback data feature, the common data playback feature comprising an indication of: a speaker, a topic, an audio content, a visual content, an application that is presented, or a meeting attendees screen that is presented;
determining a start time of the contiguous portion of the meeting recording that corresponds to a first change of the common data playback feature;
determining an end time of the contiguous portion of the meeting recording that corresponds to a second change of the common data playback feature; and
determining at least one of the respective segment or the prior segment of the meeting recording as the contiguous portion of the meeting recording from the start time to the end time.

### Claim 7 (depends on 1)

The computerized method of claim 1, wherein time-stretching the respective segment comprises adjusting a playback speed of the respective segment of the meeting recording from the default playback speed to the adaptive playback speed while maintaining a pitch of the respective segment of the meeting recording.

### Claim 8 (depends on 1)

The computerized method of claim 1, wherein determining the at least one playback data feature comprises:
detecting a user input indicative of accessing a previous portion of the meeting recording;
determining that recency of the meeting recording being played or the meeting recording being accessed is within a recency threshold of time; and
based on the recency being within the recency threshold of time, determining that a topic of the previous portion of the meeting corresponds to the at least one playback data feature, wherein the respective segment is time-stretched based on the topic corresponding to the at least one playback data feature.

### Claim 9 (depends on 1)

The computerized method of claim 1, further comprising determining at least one of the respective segment or the prior segment of the meeting recording by:
determining a change in sound parameters, of audio of the meeting recording, corresponding to a start time;
determining whether the change in the sound parameters corresponds to an utterance or a gap;
determining another change in the sound parameters, of the meeting recording, corresponding to an end time, wherein the utterance or the gap has a duration defined between the start time and the end time;
determining that at least one of the respective segment or the prior segment corresponds to the utterance or the gap; and
classifying at least one of the respective segment or the prior segment based on whether at least one of the respective segment or the prior segment corresponds to the utterance or the gap, wherein at least one of the respective segment or the prior segment is time-stretched based on the classification.

### Claim 10 (depends on 1)

The computerized method of claim 1, wherein the at least one playback data feature comprises:
a user feature specific to a particular user; and
a content feature specific to content of the meeting recording.

### Claim 11 (depends on 1)

The computerized method of claim 1, wherein the at least one playback data feature comprises at least one of a topic of the meeting recording, a type of meeting recording, an identity of a speaker in the meeting recording, a relationship of the speaker to a viewer, a duration of the meeting recording, a duration of pauses in the meeting recording, a transition from a first speaker to a second speaker different from the first speaker, a timing constraint associated with a calendar application, a rate of words per period of time, visual feedback indicative of a level of user engagement with the meeting recording from a wearable device, or contextual metadata expressed as data features indicative of meeting invitees, meeting attendees, or a type of meeting.

### Claim 12

Computer storage media having computer-executable instructions embodied thereon, that, when executed by at least one computer processor, cause computing operations to be performed, the operations comprising:
receiving, from a computing device, a request to access a meeting recording;
accessing the meeting recording comprising a plurality of time-stretched segments presentable at a corresponding adaptive playback speed and that have been generated based on at least one playback data feature from user-meeting data associated with the meeting recording, wherein the corresponding adaptive playback speed is determined based on visual content associated with the meeting recording and based on a ratio between a first word count of a prior segment and a second word count of a respective segment, wherein the respective segment is time-stretched to the corresponding adaptive playback speed;
subsequent to receiving the request, presenting a graphical user interface (GUI) comprising a stream region and a playback timeline region separate from the stream region, the playback timeline region comprising an indication corresponding to each time-stretched segment of the plurality of time-stretched segments of the meeting recording; and
presenting, on the computing device, the meeting recording in the stream region based on the plurality of time-stretched segments and the corresponding adaptive playback speed.

### Claim 13 (depends on 12)

The computer storage media of claim 12, wherein the corresponding adaptive playback speed is further determined based on a determination that the first word count differs from the second word count per period of time.

### Claim 14 (depends on 13)

The computer storage media of claim 13, wherein the corresponding adaptive playback speed is applied to the respective segment so that the word count, per the period of time, of the time-stretched respective segment and the prior segment are substantially equal, and wherein the respective segment of the meeting recording is time-stretched to the adaptive playback speed to coordinate audio of the meeting recording with the visual content.

### Claim 15 (depends on 12)

The computer storage media of claim 12, wherein the operations further comprise:
receiving a first input indicative of hovering over a segment of the meeting recording;
in response to receiving the first input, causing presentation of a window comprising a plurality of playback speed options; and
receiving a second input indicative of selecting a playback speed option, wherein the corresponding adaptive playback speed for the respective segment changes to correspond to the playback speed of the selected playback speed option.

### Claim 16 (depends on 12)

The computer storage media of claim 12, wherein the plurality of time-stretched segments are visually distinct, on the playback timeline region, from a plurality of default segments that are not time-stretched.

### Claim 17 (depends on 12)

The computer storage media of claim 12, wherein the operations further comprise determining a weight for each time-stretched segment of a plurality of time-stretched segments of the meeting recording, wherein each weight defines a corresponding time-stretching for a corresponding time-stretched segment of the plurality of time-stretched segments, wherein the updated meeting recording is playable based on the weight for each time-stretched segment.

### Claim 18 (depends on 12)

The computer storage media of claim 12, wherein the operations further comprise traversing a progress indication along the playback timeline region based on the meeting recording being played.

### Claim 19

A computer system comprising:
at least one processor; and
computer memory having computer-readable instructions embodied thereon, that, when executed by the at least one processor, cause the computer system to perform operations comprising:
receiving user-meeting data associated with a meeting recording playable at a default playback speed;
dividing the meeting recording into a plurality of segments;
determining, based on the user-meeting data and for at least one segment of the plurality of segments, at least one playback data feature by:
detecting a user input indicative of accessing a previous portion of the meeting recording;
determining that a recency of the meeting recording being played or the meeting recording being accessed is within a recency threshold of time; and
based on the recency being within the recency threshold of time, determining that a topic of the previous portion of the meeting corresponds to the at least one playback data feature;
based at least in part on the at least one playback data feature, determining, for the at least one segment of the plurality of segments, a corresponding adaptive playback speed that is faster or slower than the default playback speed;
time-stretching the at least one segment of the plurality of segments into a time-stretched segment based on the corresponding adaptive playback speed; and
causing the meeting recording to be provided with the time-stretched segment playable at the corresponding adaptive playback speed.

### Claim 20 (depends on 19)

The computer system of claim 19, wherein the operations further comprise determining a ratio between a first word count of a prior segment and a second word count of the at least one segment, wherein the ratio is applied to the at least one segment so that the word count, per period of time, of the time-stretched segment and the prior segment is substantially equal, wherein the corresponding adaptive playback speed is further determined based on the ratio.
