Speaker recognition through NLP and CWT modeling.

PDF Version Also Available for Download.

Description

The objective of this research is to develop a system capable of identifying speakers on wiretaps from a large database (>500 speakers) with a short search time duration (<30 seconds), and with better than 90% accuracy. Much previous research in speaker recognition has led to algorithms that produced encouraging preliminary results, but were overwhelmed when applied to populations of more than a dozen or so different speakers. The authors are investigating a solution to the ''huge population'' problem by seeking two completely different kinds of characterizing features. These features are extracted using the techniques of Neuro-Linguistic Programming (NLP) and the ... continued below

Physical Description

13 p.

Creation Information

Brown-VanHoozer, A.; Kercel, S. W. & Tucker, R. W. June 23, 1999.

Context

This article is part of the collection entitled: Office of Scientific & Technical Information Technical Reports and was provided by UNT Libraries Government Documents Department to Digital Library, a digital repository hosted by the UNT Libraries. It has been viewed 11 times . More information about this article can be viewed below.

Who

People and organizations associated with either the creation of this article or its content.

Sponsor

Publisher

Provided By

UNT Libraries Government Documents Department

Serving as both a federal and a state depository library, the UNT Libraries Government Documents Department maintains millions of items in a variety of formats. The department is a member of the FDLP Content Partnerships Program and an Affiliated Archive of the National Archives.

Contact Us

What

Descriptive information to help identify this article. Follow the links below to find similar items on the Digital Library.

Description

The objective of this research is to develop a system capable of identifying speakers on wiretaps from a large database (>500 speakers) with a short search time duration (<30 seconds), and with better than 90% accuracy. Much previous research in speaker recognition has led to algorithms that produced encouraging preliminary results, but were overwhelmed when applied to populations of more than a dozen or so different speakers. The authors are investigating a solution to the ''huge population'' problem by seeking two completely different kinds of characterizing features. These features are extracted using the techniques of Neuro-Linguistic Programming (NLP) and the continuous wavelet transform (CWT). NLP extracts precise neurological, verbal and non-verbal information, and assimilates the information into useful patterns. These patterns are based on specific cues demonstrated by each individual, and provide ways of determining congruency between verbal and non-verbal cues. The primary NLP modalities are characterized through word spotting (or verbal predicates cues, e.g., see, sound, feel, etc.) while the secondary modalities would be characterized through the speech transcription used by the individual. This has the practical effect of reducing the size of the search space, and greatly speeding up the process of identifying an unknown speaker. The wavelet-based line of investigation concentrates on using vowel phonemes and non-verbal cues, such as tempo. The rationale for concentrating on vowels is there are a limited number of vowels phonemes, and at least one of them usually appears in even the shortest of speech segments. Using the fast, CWT algorithm, the details of both the formant frequency and the glottal excitation characteristics can be easily extracted from voice waveforms. The differences in the glottal excitation waveforms as well as the formant frequency are evident in the CWT output. More significantly, the CWT reveals significant detail of the glottal excitation waveform.

Physical Description

13 p.

Notes

OSTI as DE00011824

Medium: P; Size: 13 pages

Source

  • 15th Annual NDIA Security Technology Symposium and Exhibition, Norfolk, VA (US), 06/14/1999--06/17/1999

Language

Item Type

Identifier

Unique identifying numbers for this article in the Digital Library or other systems.

  • Report No.: ANL/ED/CP-99102
  • Grant Number: W-31109-ENG-38
  • Office of Scientific & Technical Information Report Number: 11824
  • Archival Resource Key: ark:/67531/metadc624500

Collections

This article is part of the following collection of related materials.

Office of Scientific & Technical Information Technical Reports

Reports, articles and other documents harvested from the Office of Scientific and Technical Information.

Office of Scientific and Technical Information (OSTI) is the Department of Energy (DOE) office that collects, preserves, and disseminates DOE-sponsored research and development (R&D) results that are the outcomes of R&D projects or other funded activities at DOE labs and facilities nationwide and grantees at universities and other institutions.

What responsibilities do I have when using this article?

When

Dates and time periods associated with this article.

Creation Date

  • June 23, 1999

Added to The UNT Digital Library

  • June 16, 2015, 7:43 a.m.

Description Last Updated

  • April 7, 2017, 1:13 p.m.

Usage Statistics

When was this article last used?

Yesterday: 0
Past 30 days: 1
Total Uses: 11

Interact With This Article

Here are some suggestions for what to do next.

Start Reading

PDF Version Also Available for Download.

Citations, Rights, Re-Use

Brown-VanHoozer, A.; Kercel, S. W. & Tucker, R. W. Speaker recognition through NLP and CWT modeling., article, June 23, 1999; Illinois. (digital.library.unt.edu/ark:/67531/metadc624500/: accessed December 18, 2017), University of North Texas Libraries, Digital Library, digital.library.unt.edu; crediting UNT Libraries Government Documents Department.