de.mpg.escidoc.pubman.appbase.FacesBean
English
 
HelpDisclaimerContact usLogin
  Advanced SearchBrowse

Item

 
 
 
 
DownloadE-Mail
  ‘On-line early recognition’ of polysyllabic words in continuous speech

Scharenborg, O., Boves, L., & Ten Bosch, L. (2004). ‘On-line early recognition’ of polysyllabic words in continuous speech. In S. Cassidy, F. Cox, R. Mannell, & P. Sallyanne (Eds.), Proceedings of the Tenth Australian International Conference on Speech Science & Technology (pp. 387-392). Canberra: Australian Speech Science and Technology Association Inc.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0012-D23D-0 Version Permalink: http://hdl.handle.net/11858/00-001M-0000-0012-D23F-C
Genre: Conference Paper

Files

show Files
hide Files
:
75EEFCFDd01.pdf (Publisher version), 102KB
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Scharenborg, Odette1, Author              
Boves, Lou1, Author
Ten Bosch, Louis2, Author              
Affiliations:
1Radboud University Nijmegen, The Netherlands, escidoc:persistent22              
2Centre for Language Studies, Radboud University, escidoc:55238              

Content

show
hide
Free keywords: -
 Abstract: In this paper, we investigate the ability of SpeM, our recognition system based on the combination of an automatic phone recogniser and a wordsearch module, to determine as early as possible during the word recognition process whether a word is likely to be recognised correctly (this we refer to as ‘on-line’ early word recognition). We present two measures that can be used to predict whether a word is correctly recognised: the Bayesian word activation and the amount of available (acoustic) information for a word. SpeM was tested on 1,463 polysyllabic words in 885 continuous speech utterances. The investigated predictors indicated that a word activation that is 1) high (but not too high) and 2) based on more phones is more reliable to predict the correctness of a word than a similarly high value based on a small number of phones or a lower value of the word activation.

Details

show
hide
Language(s): eng - English
 Dates: 2004
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: Tenth Australian International Conference on Speech Science & Technology
Place of Event: Sydney, Australia
Start-/End Date: 2004-12-08 - 2004-12-10

Legal Case

show

Source 1

show
hide
Title: Proceedings of the Tenth Australian International Conference on Speech Science & Technology
Source Genre: Proceedings
 Creator(s):
Cassidy, Steve, Editor
Cox, Felicity, Editor
Mannell, Robert, Editor
Sallyanne, Palethorpe, Editor
Affiliations:
-
Publ. Info: Canberra : Australian Speech Science and Technology Association Inc
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 387 - 392 Identifier: URI: http://www.assta.org/sst/2004/
ISBN: 0 9581946 1 0