Loading...
Please wait, while we are loading the content...
Similar Documents
Perception and Production by a Self-organizing Neural Network
| Content Provider | Semantic Scholar |
|---|---|
| Author | Cohen, Michael A. Grossberg, Stephen Stork, David G. |
| Copyright Year | 2004 |
| Abstract | Considerations of the real-time self-organization of neural networks for speech recognition and production have lead to a new understanding of several key issues in such networks, most notably a definition of new processing units and functions of hierarchical levels in the auditory system. An important function of a particular neural level in the auditory system is to provide a partially-compressed code, mapped to the articulatory system, to permit imitation of novel sounds. Furthermore, top-down priming signals from the articulatory system to the auditory system help to stabilize the emerging auditory code. These structures help explain results from the motor theory, which states that speech is analyzed by how it would be produced. Higher stages of processing require chunking or unitization of the emerging language code, an example of a classical grouping problem. The partially compressed auditory codes are further compressed into item codes (e.g., phonemic segments), which are stored in a working memory representation whose shortterm memory pattern is its code. A masking field level receives input from this working memory and encodes this input into list chunks, whose top-down signals organize the items in working memory into coherent groupings with invariant properties. This total architecture sheds new light on key speech issues such as coarticulation, analysis-by-synthesis, motor theory, categorical perception, invariant speech perception, word superiority, and phonemic restoration. 1. The Learning of Language Units During a human's early years, an exquisitely subtle and sensitive speech recognition and production system develops. These two systems develop to be well-matched to each other, 'enabling rapid and reliable broadcast and reception of linguistic information. The development of these systems can be viewed as resulting from two fundamental processes: self-organization through circular reaction and through chunking or unitization. This chapter sketches some issues concerning these processes in speech and provides a summary of its key neural components, developed to address more general cognitive problems. 2. Low Stages or Processing: Circular Reactions and the Emerging Auditory and Motor Codes The concept of circular reaction (Piaget, 1963) is illustrated in Figure 1. For our purposes, the reaction links the motor or articulatory system (mouth, tongue, velum, etc., and the neural structures controlling them) with the auditory system (ear and its neural M.A.C. was supported in part by the Air Force Office of Scientific Research (AFOSR F49620-86-C-0037) and the National Science Foundation (NSF IRI-84-17756), S.G. was supported in part by the Air Force Office of Scientific Research (AFOSR F49620-86-C0037 and AFOSR F49620-87-C-0018), and D.G.S. was supported in part by the Air Force Office of Scientifi( Research (AFOSR F49620-86-C-0037). Acknowledgements: We wish to thank Cynthia Suchta and Carol Yanakakis for their valuable assistance in the preparation of the manuscript. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.cns.bu.edu/Profiles/Grossberg/CohGroStork1988LeeChapter.pdf |
| Language | English |
| Access Restriction | Open |
| Subject Keyword | Artificial neural network Auditory system CNS disorder Circuit restoration Cognition Disorders Coherence (physics) Cynthia Dwork IBM Notes Language code Linguistics Manuscripts Memory Disorders Motor theory of speech perception Nephrogenic Systemic Fibrosis Neural Network Simulation Oral cavity Organizing (structure) Piaget's theory of cognitive development Priming Exercise Production system (computer science) Real-time transcription Self-organization Self-organizing map Shallow parsing Speech coding Speech recognition Top-down and bottom-up design negative regulation of endoplasmic reticulum tubular network organization |
| Content Type | Text |
| Resource Type | Article |
