Home News About Us Contact Contributors Disclaimer Privacy Policy Help FAQ

Home
Search
Quick Search
Advanced
Fulltext
Browse
Collections
Persons
My eDoc
Session History
Login
Name:
Password:
Documentation
Help
Support Wiki
Direct access to
document ID:


          Institute: MPI für Psycholinguistik     Collection: Decoding Continuous Speech     Display Documents



  history
ID: 248488.0, MPI für Psycholinguistik / Decoding Continuous Speech
How should a speech recognizer work?
Authors:Scharenborg, Odette; Norris, Dennis; Ten Bosch, Louis; McQueen, James M.
Language:English
Date of Publication (YYYY-MM-DD):2005
Title of Journal:Cognitive Science
Volume:29
Issue / Number:6
Start Page:867
End Page:918
Review Status:Peer-review
Audience:Experts Only
Abstract / Description: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.
External Publication Status:published
Document Type:Article
Communicated by:James McQueen
Affiliations:MPI für Psycholinguistik
Identifiers:DOI:10.1207/s15516709cog0000_37
Full Text:
Sorry, no privileges
The scope and number of records on eDoc is subject to the collection policies defined by each institute - see "info" button in the collection browse view.