English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  How should a speech recognizer work?

Scharenborg, O., Norris, D., Ten Bosch, L., & McQueen, J. M. (2005). How should a speech recognizer work? Cognitive Science, 29(6), 867-918. doi:10.1207/s15516709cog0000_37.

Item is

Files

show Files
hide Files
:
Scharenborg_2005_how should.pdf (Publisher version), 676KB
File Permalink:
-
Name:
Scharenborg_2005_how should.pdf
Description:
-
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
eDoc_access: USER
License:
-

Locators

show

Creators

show
hide
 Creators:
Scharenborg, Odette, Author
Norris, Dennis1, 2, Author
Ten Bosch, Louis, Author
McQueen, James M.1, 2, Author           
Affiliations:
1Language Comprehension Group, MPI for Psycholinguistics, Max Planck Society, ou_55203              
2Decoding Continuous Speech, MPI for Psycholinguistics, Max Planck Society, ou_55222              

Content

show
hide
Free keywords: -
 Abstract: Although researchers studying human speech recognition (HSR) and automatic speech recognition (ASR) share a common interest in how information processing systems (human or machine) recognize spoken language, there is little communication between the two disciplines. We suggest that this lack of communication follows largely from the fact that research in these related fields has focused on the mechanics of how speech can be recognized. In Marr's (1982) terms, emphasis has been on the algorithmic and implementational levels rather than on the computational level. In this article, we provide a computational-level analysis of the task of speech recognition, which reveals the close parallels between research concerned with HSR and ASR. We illustrate this relation by presenting a new computational model of human spoken-word recognition, built using techniques from the field of ASR that, in contrast to current existing models of HSR, recognizes words from real speech input.

Details

show
hide
Language(s): eng - English
 Dates: 2005
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: eDoc: 248488
DOI: 10.1207/s15516709cog0000_37
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Cognitive Science
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 29 (6) Sequence Number: - Start / End Page: 867 - 918 Identifier: -