Authors:

Scharenborg, O., NORRIS, D., ten Bosch, L., & McQueen, J. M.

Reference:

Year of publication:

2005

CBU number:

6789

Abstract:

Although researchers studying human speech recognition and automatic speech recognition 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 the present paper, we provide a computational-level analysis of the task of speech recognition which reveals the close parallels between research concerned with human and automatic speech recognition. We illustrate this relationship by presenting a new computational model of human spoken word recognition, built using techniques from the field of automatic speech recognition that, in contrast to current existing models of human speech recognition, recognizes words from real speech input.