2 |
Distributed semantics in a neural network model of human speech recognition
|
|
|
|
In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol 43, iss 43 (2021)
|
|
BASE
|
|
Show details
|
|
3 |
Lexically-Mediated Compensation for Coarticulation in Older Adults
|
|
|
|
In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol 43, iss 43 (2021)
|
|
BASE
|
|
Show details
|
|
4 |
Lexically-Mediated Compensation for Coarticulation in Older Adults ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Lexically-Mediated Compensation for Coarticulation in Older Adults ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Distributed semantics in a neural network model of human speech recognition ...
|
|
|
|
Abstract:
While there are interesting correspondences between form and meaning in many languages, psycholinguists conventionally consider them to be marginal, as they affect only a small subset of words. As such, a common simplification in computational models is to use empirically- or theoretically-motivated representations for form and random vectors for semantics. We recently introduced a novel model of human speech recognition, EARSHOT, which maps spectral slices (form) to pseudo-semantic patterns (sparse random vectors [SRVs]). Here, we replace SRVs with SkipGram vectors. Empirically-based semantics allow the model to learn more quickly and, surprisingly, exhibit more realistic form competition effects. These improved form competition effects do not depend on the particular form-to-meaning mapping in the training lexicon; rather, they arise as a result of the nontrivial output structure. These results suggest that while form-meaning mappings may be mainly arbitrary, realistic semantics afford important ...
|
|
Keyword:
Cognitive Science
|
|
URL: https://dx.doi.org/10.48448/w947-mj25 https://underline.io/lecture/27303-distributed-semantics-in-a-neural-network-model-of-human-speech-recognition
|
|
BASE
|
|
Hide details
|
|
7 |
Listener expectations and the perceptual accommodation of talker variability: A pre-registered replication
|
|
|
|
In: Atten Percept Psychophys (2021)
|
|
BASE
|
|
Show details
|
|
8 |
Does signal reduction imply predictive coding in models of spoken word recognition?
|
|
|
|
In: Psychon Bull Rev (2021)
|
|
BASE
|
|
Show details
|
|
17 |
Friends in Low-Entropy Places: Orthographic Neighbor Effects on Visual Word Identification Differ Across Letter Positions
|
|
|
|
In: Cogn Sci (2020)
|
|
BASE
|
|
Show details
|
|
18 |
Is that a pibu or a pibo? Children with reading and language deficits show difficulties in learning and overnight consolidation of phonologically similar pseudowords
|
|
|
|
In: Dev Sci (2020)
|
|
BASE
|
|
Show details
|
|
19 |
Boosting lexical support does not enhance lexically guided perceptual learning
|
|
|
|
In: J Exp Psychol Learn Mem Cogn (2020)
|
|
BASE
|
|
Show details
|
|
|
|