Speech recognition and summarization

• US 8,612,211 B1
• Filed: 01/17/2013
• Issued: 12/17/2013
• Est. Priority Date: 09/10/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Shires, Glen, Swigart, Sterling, Zolla, Jonathan, Gauci, Jason J.
• Primary Examiner(s): GUERRA-ERAZO, EDGAR X
• Application Number:
  US13/743,838
• Time in Patent Office: 334 Days
• Field of Search: 704/235, 704/246, 704/270, 704/270.1, 704/275, 704/9, 704/10, 704/243
• US Class Current: 704/9
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 21/10 Transforming into visible information
• CPC Class Codes: H04N 7/15 Conference systems

Abstract

The subject matter of this specification can be embodied in, among other things, a method that includes receiving two or more data sets each representing speech of a corresponding individual attending an internet-based social networking video conference session, decoding the received data sets to produce corresponding text for each individual attending the internet-based social networking video conference, and detecting characteristics of the session from a coalesced transcript produced from the decoded text of the attending individuals for providing context to the internet-based social networking video conference session.

Claims

1. A method comprising:

in one or more processing devices, executing instructions to perform operations comprising;

receiving two or more data sets, each data set representing speech of a corresponding individual attending a social networking video conference session;

decoding the received data sets to produce corresponding text for each individual attending the social networking video conference session;

detecting one or more topics of the social networking video conference session from a transcript produced from the text for each individual attending the social networking video conference session; and

providing, to one or more of the attending individuals of the social networking video conference session, context relating to the one or more topics of the social networking video conference session detected from the transcript produced from the text for each individual attending the social networking video conference session.

2. The method of claim 1, wherein detecting one or more topics of the social networking video conference session from a transcript produced from the text for each individual attending the social networking video conference session further comprises:

identifying one or more keywords from the transcript produced from the text; and

detecting one or more topics of the social networking video conference session based on the one or more keywords identified from the transcript produced from the text.

3. The method of claim 1, wherein detecting one or more topics of the social networking video conference session from the transcript produced from the text for each individual attending the social networking video conference session includes at least one of detecting a temporal length of the social networking video conference session and detecting a repetitive use of one or more words.

4. The method of claim 1, further comprising:

detecting characteristics of the social networking video conference session from the two or more received data sets; and

detecting one or more topics of the social networking video conference session based on the transcript produced from the text for each individual attending the social networking video conference session and the detected characteristics.

5. The method of claim 4, wherein detecting characteristics of the social networking video conference session includes monitoring at least one of the volume of the speech represented in the two or more received data sets and the presented speed of the speech represented in the two or more received data sets.

6. The method of claim 1, further comprising:

detecting characteristics of the social networking video conference session attending individuals from other corresponding data sets; and

detecting one or more topics of the social networking video conference session based on the transcript produced from the text for each individual attending the social networking video conference session and the detected characteristics.

7. The method of claim 6, wherein detecting characteristics of the social networking video conference session attending individuals from the other corresponding data sets includes detecting physical features of the attending individuals.

8. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

receiving two or more data sets, each data set representing speech of a corresponding individual attending a social networking video conference session;

decoding the received data sets to produce corresponding text for each individual attending the social networking video conference session;

detecting one or more topics of the social networking video conference session from a transcript produced from the text for each individual attending the social networking video conference session; and

providing, to one or more of the attending individuals of the social networking video conference session, context relating to the one or more topics of the social networking video conference session detected from the transcript produced from the text for each individual attending the social networking video conference session.

9. The system of claim 8, wherein detecting one or more topics of the social networking video conference session from a transcript produced from the text for each individual attending the social networking video conference session further comprises:

identifying one or more keywords from the transcript produced from the text; and

detecting one or more topics of the social networking video conference session based on the one or more keywords identified from the transcript produced from the text.

10. The system of claim 8, wherein detecting one or more topics of the social networking video conference session from the transcript produced from the text for each individual attending the social networking video conference session includes at least one of detecting a temporal length of the social networking video conference session and detecting a repetitive use of one or more words.

11. The system of claim 8, the operations further comprising:

detecting characteristics of the social networking video conference session from the two or more received data sets; and

detecting one or more topics of the social networking video conference session based on the transcript produced from the text for each individual attending the social networking video conference session and the detected characteristics.

12. The system of claim 11, wherein detecting characteristics of the social networking video conference session includes monitoring at least one of the volume of the speech represented in the two or more received data sets and the presented speed of the speech represented in the two or more received data sets.

13. The system of claim 8, the operations further comprising:

detecting characteristics of the social networking video conference session attending individuals from other corresponding data sets; and

detecting one or more topics of the social networking video conference session based on the transcript produced from the text for each individual attending the social networking video conference session and the detected characteristics.

14. The system of claim 13, wherein detecting characteristics of the social networking video conference session attending individuals from the other corresponding data sets includes detecting physical features of the attending individuals.

15. One or more non-transitory machine-readable media storing instructions that are executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

receiving two or more data sets, each data set representing speech of a corresponding individual attending a social networking video conference session;

decoding the received data sets to produce corresponding text for each individual attending the social networking video conference session;

detecting one or more topics of the social networking video conference session from a transcript produced from the text for each individual attending the social networking video conference session; and

providing, to one or more of the attending individuals of the social networking video conference session, context relating to the one or more topics of the social networking video conference session detected from the transcript produced from the text for each individual attending the social networking video conference session.

16. The machine-readable media of claim 15, wherein detecting one or more topics of the social networking video conference session from a transcript produced from the text for each individual attending the social networking video conference session further comprises:

identifying one or more keywords from the transcript produced from the text; and

detecting one or more topics of the social networking video conference session based on the one or more keywords identified from the transcript produced from the text.

17. The machine-readable media of claim 15, wherein detecting one or more topics of the social networking video conference session from the transcript produced from the text for each individual attending the social networking video conference session includes at least one of detecting a temporal length of the social networking video conference session and detecting a repetitive use of one or more words.

18. The machine-readable media of claim 15, the operations further comprising:

detecting characteristics of the social networking video conference session attending individuals from other corresponding data sets; and

detecting one or more topics of the social networking video conference session based on the transcript produced from the text for each individual attending the social networking video conference session and the detected characteristics.

19. The machine-readable media of claim 15, the operations further comprising:

detecting characteristics of the social networking video conference session from the two or more received data sets; and

detecting one or more topics of the social networking video conference session based on the transcript produced from the text for each individual attending the social networking video conference session and the detected characteristics.

20. The machine-readable media of claim 19, wherein detecting characteristics of the social networking video conference session includes monitoring at least one of the volume of the speech represented in the two or more received data sets and the presented speed of the speech represented in the two or more received data sets.