System and method of improving communication in a speech communication system

• US 9,633,668 B2
• Filed: 07/15/2015
• Issued: 04/25/2017
• Est. Priority Date: 06/07/2013
• Status: Active Grant

• Current Assignee: RingCentral Incorporated
• Original Assignee: Unify GmbH & Co. KG (Atos SE)
• Inventors: Totzke, Jurgen
• Primary Examiner(s): Desir, Pierre-Louis
• Assistant Examiner(s): Tzeng, Forrest F
• Application Number:
  US14/799,689
• Publication Number:
  US 20150317996A1
• Time in Patent Office: 650 Days
• Field of Search: 704 9, 704270, 704251, 704257, 704E15001, 704E15045
• CPC Class Codes: G06F 3/04812 Interaction techniques based on cursor appearance or behaviour, e.g. being affected by the presence of displayed objects
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 15/08 Speech classification or search
• 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 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 21/02 Speech enhancement, e.g. noise reduction or echo cancellation reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08
• CPC Class Codes: G10L 21/10 Transforming into visible information

Abstract

A speech communication system and a method of improving communication in such a speech communication system between at least a first user and a second user may be configured so the system (a) transcribes a recorded portion of a speech communication between the at least first and second user to form a transcribed portion, (b) selects and marks at least one of the words of the transcribed portion which is considered to be a keyword of the speech communication, (c) performs a search for each keyword and produces at least one definition for each keyword, (d) calculates a trustworthiness factor for each keyword, each trustworthiness factor indicating a calculated validity of the respective definition(s), and (e) displays the transcribed portion as well as each of the keywords together with the respective definition and the trustworthiness factor thereof to at least one of the first user and the second user.

Claims

1. A method of improving communication in a speech communication system between at least a first user and a second user, the speech communication system comprising at least one processor communicatively connected to non-transitory memory, the method comprising:

a) transcribing, by the system, a recorded portion of a speech communication between the at least first and second user to form a transcribed portion,

b) selecting and marking, by the system, at least one of the words of the transcribed portion which is considered to be a keyword of the speech communication,

c) performing, by the system, a search for each keyword and produces at least one definition for each keyword that identifies a meaning of that keyword,

d) calculating, by the system, a trustworthiness factor for each keyword, each trustworthiness factor indicating a calculated validity of a respective definition for a respective keyword; and

e) displaying, by the system, the transcribed portion such that each keyword within the transcribed portion is highlighted in the display of the transcribed portion;

f) in response to a pointer being positioned over a displayed highlighted keyword of the displayed transcribed portion or selection of the displayed keyword, displaying the at least one definition of the keyword together with the calculated trustworthiness factor for each displayed definition over the displayed transcribed portion.

2. The method of claim 1, wherein each definition is a generated dictionary definition and wherein the system calculating the trustworthiness factor for each keyword comprises:

the system performing;

a semantic search using taxonomies in order to generate a taxonomy correction factor for determining the trustworthiness factor for each definition;

a similarity checking which takes into account similarity of different definitions for each keyword in order to generate a similarity correction factor for determining the trustworthiness factor for each definition; and

a sentiment detection which takes into account sentiment with respect to a definition for each keyword to generate a sentiment correction factor for determining the trustworthiness factor for that definition; and

determining the trustworthiness factor for each definition based on the taxonomy correction factor, the similarity correction factor, and the sentiment correction factor for that keyword; and

wherein the system performing the search for each keyword comprises;

the system communicating with at least one information space communicatively connected to the system via at least one network connection to identify at least one definition for each keyword for producing a definition for that keyword.

3. The method of claim 1, comprising:

performing a spell-check of the transcribed portion using at least one regular glossary and/or at least one domain glossary.

4. The method of claim 1, wherein:

step b) comprises an automatic selecting of the keywords by the system and manually selecting of the keywords by a user and/or by a community of users using the system.

5. The method of claim 1, wherein:

step c) comprises a search in a structured and/or in an unstructured data repository.

6. The method of claim 1, wherein:

step d) comprises the system performing a semantic search using ontologies.

7. The method of claim 1, wherein:

step d) comprises the system performing a semantic search using taxonomies in order to generate a taxonomy correction factor for modifying the trustworthiness factor.

8. The method of claim 1, wherein:

step d) comprises the system carrying out similarity checking which takes into account similarity of different definitions of a respective keyword in order to generate a similarity correction factor for modifying the trustworthiness factor.

9. The method of claim 1, wherein:

step d) comprises the system carrying out sentiment detection which takes into account the sentiment with respect to at least one definition of at least one keyword in order to generate a sentiment correction factor for modifying the trustworthiness factor.

10. The method of claim 1, wherein the speech communication results in a communication thread and wherein a glossary of the communication thread is created and regularly updated.

11. A non-transitory tangible computer-readable medium comprising a computer program that defines a method that is performed by a communication system when a processor unit of the system runs the program, the method comprising:

a) the system transcribing a recorded portion of a speech communication between the at least first and second user to form a transcribed portion,

b) the system selecting and marking at least one of the words of the transcribed portion which is considered to be a keyword of the speech communication,

c) the system performing a search for each keyword and produces at least one definition for each keyword that identifies a meaning of that keyword,

d) the system calculating a trustworthiness factor for each keyword, each trustworthiness factor indicating a calculated validity of a respective definition for a respective keyword, and

e) the system displaying the transcribed portion such that each keyword within the transcribed portion is highlighted in the display of the transcribed portion;

f) in response to a pointer being positioned over a displayed highlighted keyword of the transcribed portion or selection of the displayed highlighted keyword, displaying the at least one definition of the keyword together with the trustworthiness factor for each displayed definition of that keyword over the displayed transcribed portion.

12. A speech communication system comprising:

non-transitory memory;

a transcription unit, the transcription unit configured to transcribe a recorded portion of a speech communication between the at least first and second user stored in the memory to form a transcribed portion,

a selecting unit, the selecting unit configured to select and mark at least one of the words of the transcribed portion which is considered to be a keyword of the speech communication,

a search unit, the search unit configured to perform at least one search for each keyword and producing at least one definition for each keyword that identifies a meaning of that keyword,

a trustworthiness unit, the trustworthiness unit configured to calculate a trustworthiness factor for each keyword, each trustworthiness factor indicating a calculated validity of a respective definition for a respective keyword; and

a display unit, the display unit configured to display the transcribed portion such that each keyword within the transcribed portion is highlighted in the display of the transcribed portion, the display unit configured to display the at least one definition for the keyword together with the trustworthiness factor for each displayed definition of the keyword over the displayed transcribed portion in response to a selection of the displayed keyword or a pointer being positioned over the displayed keyword.

13. The speech communication system of claim 12, further comprising:

a recording unit, the recording unit configured to record real-time speech communication.

14. The speech communication system of claim 13, further comprising:

a spell-check unit, the spell-check unit configured to spell check the transcribed portion using at least of a regular domain glossary and a domain glossary.

15. The speech communication system of claim 12, wherein the selection unit is configured to automatically select at least one of the words based on one of the keywords and the system further comprising:

an input device configured such that a manual selecting of the keywords by at least one user is inputtable to the system.

16. The speech communication system of claim 12, further comprising:

a search unit, the search unit configured to search in a structured and/or in an unstructured data repository.

17. The speech communication system of claim 12, further comprising:

a semantic search unit, the semantic search unit configured to perform a semantic search using ontologies.

18. The speech communication system of claim 12, further comprising:

a semantic search unit, the semantic search unit configured to perform a semantic search using taxonomies in order to generate a taxonomy correction factor that is used to calculate the trustworthiness factor.

19. The speech communication system of claim 18, further comprising:

a similarity check unit, the similarity check unit configured to carry out a similarity checking step which takes into account the similarity of various definitions of a respective keyword in order to generate a similarity correction factor that is used to calculate the trustworthiness factor.

20. The speech communication system of claim 19, further comprising:

a sentiment check unit, the sentiment check unit configured to carry out a step of sentiment detection which takes into account the sentiment with respect to at least one definition of at least one keyword in order to generate a sentiment correction factor that is used to calculate the trustworthiness factor.