Systems and methods for transcript processing

• US 10,387,548 B2
• Filed: 04/12/2016
• Issued: 08/20/2019
• Est. Priority Date: 04/16/2015
• Status: Active Grant

• Current Assignee: Nasdaq, Inc.
• Original Assignee: Nasdaq, Inc.
• Inventors: Avore, Christopher, McNeil, Joseph, Eckels, Christian
• Primary Examiner(s): Shah, Paras D
• Application Number:
  US15/096,492
• Publication Number:
  US 20160306788A1
• Time in Patent Office: 1,225 Days
• Field of Search: 704231, 704275
• CPC Class Codes: G06F 16/638 Presentation of query results
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G06F 40/143 Markup, e.g. Standard Generalized Markup Language [SGML] or Document Type Definition [DTD]
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques

Abstract

The technology relates to systems and methods for transcribing audio of a meeting. Upon transcribing the audio, the systems and methods can parse different portions of the prescribed audio so that they may attribute the different portions to a particular speaker. These transcribed portions that are attributed to a particular speaker are made available for viewing and interacting using a graphical user interface.

Claims

1. A system configured to associate an analyzed transcript to a speaker, comprising:

a network interface device;

a processor; and

a memory, operatively coupled to the network interface device and the processor and storing computer readable instructions that, when executed by the processor, cause the system to;

obtain transcript data of a dialogue between two or more people;

parse the obtained transcript data;

identify one or more portions of the parsed transcript data based on identification information contained in one or more tags in the transcript data;

identify one or more elements in a portion, of the one or more portions, of the transcript data based on one or more delimiter types contained in the portion of the transcript data;

determine at least one speaker from the parsed transcript data by identifying at least a name of the speaker from the one or more identified elements;

associate at least a portion of spoken dialogue from the parsed transcript data to the determined speaker by linking the portion of spoken dialogue to the name of the speaker;

store the portion of the spoken dialogue and the name of the speaker in association with each other in a database; and

generate data for displaying a user interface that displays web-pages having at least a first page, a second page, and a third page, wherein;

the first page includes a layout containing a plurality of elements associated with a profile, wherein the plurality of elements includes at least market information, contact information, and at least a portion of the spoken dialogue associated with the speaker, the plurality of elements divided on the first page so that the portion of the spoken dialogue is positioned proximate to the contact information and the market information, and selection of the portion of the spoken dialogue causes display of the second page;

the second page includes;

additional dialogue associated with each of a plurality of events in which the speaker has spoken; and

a transcript button proximate to the additional dialogue associated with an event from the plurality of events in which the speaker has spoken; and

selection of the transcript button causes display of the third page, wherein the third page includes a full text version of a transcript of the event, wherein the full text version of the transcript of the event includes the portion of the spoken dialogue of the speaker and dialogue of additional speakers for the event.

2. The system of claim 1, wherein the transcript data contains first text data corresponding to a dialogue of a first speaker and an identification of the first speaker sequentially following the first text data, the first text data and the identification of the first speaker separated by at least one delimiter.

3. The system of claim 2, wherein the identification of the first speaker includes at least a name of the first speaker, an entity in which the first speaker is associated, and a title held by the first speaker.

4. The system of claim 1, wherein

the transcript data is incorporated into a structured document comprising metadata, a body of the structured document, and one or more additional identifiers, and

the metadata includes at least an event identifier, an event type name, an event story identifier, and/or an expiration data.

5. The system of claim 1, wherein

the transcript data is incorporated into a structured document comprising metadata, a body of the structured document, and one or more additional identifiers, and

the body of the structured document includes at least text of an event, one or more questions raised during the event, and one or more answers provided to the questions raised during the event.

6. The system of claim 1, wherein

the transcript data is incorporated into a structured document comprising metadata, a body of the structured document, and one or more additional identifiers, and

the one or more additional identifiers include at least a city, a company name, and/or a company identifier.

7. The system of claim 1, wherein a body of the transcript data includes portions containing organizers of an event, participants of the event, presentation content of the event, and question and answer content of the event, and wherein parsing the transcript data comprises identifying the portions containing the organizers of the event, the participants of the event, the presentation content of the event, and the question and answer content of the event based on a first type of delimiter.

8. The system of claim 1, wherein the portion of the spoken dialogue is positioned below the contact information on the first page.

9. The system of claim 1, wherein the portion of the spoken dialogue is positioned above the market information on the first page.

10. The system of claim 1, wherein a body of the transcript data includes a first portion including a listing of speakers presenting at an event, and wherein parsing the obtained transcript data comprises identifying a name of a presenter and a name of a company associated with the presenter, in the first portion, based on a first type of delimiter in the transcript data.

11. The system of claim 10, wherein parsing the obtained transcript data comprises identifying a title of the presenter, in the first portion, based on a second type of delimiter in the transcript data.

12. A non-transitory computer-readable storage medium comprising computer readable code for associating an analyzed transcript to a speaker which, when executed by a computer having one or more processors, causes the computer to:

obtain transcript data of a dialogue between two or more people;

parse the obtained transcript data based on one or more delimiters contained within the transcript data and identify one or more elements in a portion of the transcript data;

determine at least one speaker from the parsed transcript data by identifying at least a name of the speaker from the one or more identified elements;

associate at least a portion of spoken dialogue from the parsed transcript data to the determined speaker;

store the portion of the spoken dialogue in association with the name of the speaker in a database; and

generate data for displaying a user interface that displays web-pages having at least a first page, a second page, and a third page, wherein;

the first page includes a layout containing a plurality of elements associated with a profile, wherein the plurality of elements includes at least market information, contact information, and at least a portion of the spoken dialogue associated with the speaker, the plurality of elements divided on the first page so that the portion of the spoken dialogue is positioned proximate to the contact information and the market information, and selection of the portion of the spoken dialogue causes display of the second page;

the second page includes;

additional dialogue associated with each of a plurality of events in which the speaker has spoken; and

a transcript button proximate to the additional dialogue associated with an event from the plurality of events in which the speaker has spoken; and

selection of the transcript button causes display of the third page, wherein the third page includes a full text version of a transcript of the event, wherein the full text version of the transcript of the event includes the portion of the spoken dialogue of the speaker and dialogue of additional speakers for the event.

13. The non-transitory computer-readable storage medium of claim 12, wherein the transcript data contains first text data corresponding to a dialogue of a first speaker and an identification of the first speaker sequentially following the first text data, the first text data and the identification of the first speaker separated by at least one delimiter.

14. The non-transitory computer-readable storage medium of claim 13, wherein the identification of the first speaker includes at least a name of the first speaker, an entity in which the first speaker is associated, and a title held by the first speaker.

15. A method for associating an analyzed transcript to a speaker, comprising:

at an information processing apparatus having at least a memory, a transceiver, and a processor;

obtaining transcript data of a dialogue between two or more people;

parsing the obtained transcript data based on one or more delimiters contained within the transcript data and identifying one or more elements in a portion of the transcript data;

determining at least one speaker from the parsed transcript data by identifying at least a name of the speaker from the one or more identified elements;

associating at least a portion of spoken dialogue from the transcript data to the determined speaker;

storing the portion of the spoken dialogue in association with the name of the speaker in a database; and

generating data for displaying a user interface that displays web-pages having at least a first page, a second page, and a third page, wherein;

the first page includes a layout containing a plurality of elements associated with a profile, wherein the plurality of elements includes at least market information, contact information, and at least a portion of the spoken dialogue associated with the speaker, the plurality of elements divided on the first page so that the portion of the spoken dialogue is positioned proximate to the contact information and the market information, and selection of the portion of the spoken dialogue causes display of the second page;

the second page includes;

additional dialogue associated with each of a plurality of events in which the speaker has spoken; and

a transcript button proximate to the additional dialogue associated with an event from the plurality of events in which the speaker has spoken; and

selection of the transcript button causes display of the third page, wherein the third page includes a full text version of a transcript of the event, wherein the full text version of the transcript of the event includes the portion of the spoken dialogue of the speaker and dialogue of additional speakers for the event.

16. The method of claim 15, wherein the transcript data contains first text data corresponding to a dialogue of a first speaker and an identification of the first speaker sequentially following the first text data, the first text data and the identification of the first speaker separated by at least one delimiter.

17. A client device configured to generate a user interface containing information related to an analyzed transcript, comprising:

a memory storing computer readable instructions for execution;

a display device;

a network interface device; and

a processor operatively coupled to the memory, the network interface device, and the display device, the processer controlling the client device to;

request first data, stored in a database of a server, for generating a user interface providing information related to a spoken dialogue associated with a speaker;

receive the first data from the server;

construct portions of the user interface, for display by the display device, that include web-pages having at least a first page, a second page, and a third page, wherein;

the first page includes a layout containing a plurality of elements associated with a profile, wherein the plurality of elements includes at least market information, contact information, and at least a portion of the spoken dialogue associated with the speaker, the plurality of elements divided on the first page so that the portion of the spoken dialogue is positioned proximate to the contact information and the market information, and selection of the portion of the spoken dialogue causes display of the second page;

the second page includes;

additional dialogue associated with each of a plurality of events in which the speaker has spoken; and

a transcript button proximate to the additional dialogue associated with an event from the plurality of events in which the speaker has spoken; and

selection of the transcript button causes display of the third page, wherein the third page includes a full text version of a transcript of the event, wherein the full text version of the transcript of the event includes the portion of the spoken dialogue of the speaker and dialogue of additional speakers for the event.

18. The client device of claim 17, wherein the full text version of the transcript of the event containing identification of one or more speakers and their associated contribution of spoken dialogue at the event.