Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

System and Method of Text Zoning

a text zoning and text technology, applied in the field of text zoning system and method, can solve the problems of difficulty in meaningful analysis and inaccurate results

Inactive Publication Date: 2015-03-05
VERINT SYST LTD
View PDF3 Cites 207 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

The patent describes a method for identifying meaning units in a transcription of auto data. This is done by separating the transcription into multiple utterances and assigning a probability to each word in an utterance. If a word is longer than a certain threshold, it is split into two new phrases. The method also suggests which parts of the data should be further analyzed based on their linguistic context. Overall, the method enables more accurate identification of meaning units in speech data, which can improve the efficiency and accuracy of speech recognition systems.

Problems solved by technology

Without such natural cues to provide context, meaningful analysis may be difficult and inaccurate.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • System and Method of Text Zoning
  • System and Method of Text Zoning
  • System and Method of Text Zoning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0008]Meaning units are effectively the building blocks of a specific speech, interaction, or disclosure. A meaning unit can be considered to be a realization of an illocutionary force (intent), a conceptual content, a syntactic dependency (grammatical relation), and a prosodic contour. Zoning of a transcript as disclosed herein, seeks to find optimal positions of boundaries between meaning units within the transcript. In an embodiment, the transcript is an automated transcription of audio data. Embodiments as disclosed herein have been found to be more accurate in automatedly zoning transcripts. More accurate identification of meaning units both makes later analysis and analytics of the meaning units less computationally demanding and produces more accurate and meaningful results because appropriate context is available more frequently.

[0009]Referring first to FIG. 3, FIG. 3 is a flow chart that depicts an exemplary embodiment of a method 300 of audio data analysis. The method 300 ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A method of zoning a transcription of audio data includes separating the transcription of audio data into a plurality of utterances. A that each word in an utterances is a meaning unit boundary is calculated. The utterance is split into two new utterances at a work with a maximum calculated probability. At least one of the two new utterances that is shorter than a maximum utterance threshold is identified as a meaning unit.

Description

CROSS-REFERENCE TO RELATED APPLICATION[0001]The present application claims priority of U.S. Provisional Patent Application No. 61 / 872,224, filed on Aug. 30, 2013, the content of which is hereby incorporated herein by reference in its entirety.BACKGROUND[0002]In the case of automated transcription of audio data often the output transcription in likely in the form of a single text file. In many instances, the audio data in fact contains a conversation between multiple speakers. Even within a case of a single speaker, automated transcriptions will be devoid of punctuation. These natural events provide context for analysis of the content of the transcription. Without such natural cues to provide context, meaningful analysis may be difficult and inaccurate. Therefore it is desirable for an automated system and method automatedly zone or segment the transcription file.BRIEF DISCLOSURE[0003]A method of zoning a transcription of auto data includes separating the transcription of auto data i...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(United States)
IPC IPC(8): G10L15/26G10L15/18
CPCG10L15/18G10L15/26G10L15/1822G10L15/04
Inventor ROMANO, RONIHORESH, YAIRDREYFUSS, JEREMIE
Owner VERINT SYST LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products