Learning phonetic categories by learning a lexicon

By Naomi H Feldman, T. Griffiths, James L. Morgan. 2009

94 citations recorded by the source corpus.

Subfields: Computational Linguistics & Semantics, Speech & Audio

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Linguistics & Semantics

In Speech & Audio

Citations in the corpus

Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks (2019, background): “From a scientiﬁc perspective, discrete representations could be useful in cognitive models to study phonetic category learning in human infants [15–18].”
A segmental framework for fully-unsupervised large-vocabulary speech recognition (2016, background): “There is also evidence that infants are able to segment whole words from continuous speech while still learning phonetic contrasts in their native language [35,36].”
Unsupervised Word Segmentation and Lexicon Discovery Using Acoustic Word Embeddings (2016, background): “there is evidence that infants are able to segment whole words from continuous speech before phonetic contrasts in their native language have been fully learned [26], [27].”
A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition (2013, background): “Steps in this direction have been taken [16, 31, 32], but we are aware of no fully integrated system using speech data as input.”
Computational modeling of phonetic and lexical learning in early language acquisition: Existing models and future directions (2012, methodology): “Only when support from the lexical layer was utilized in order to perform context-sensitive classification, the categorization of the segments became successful [12].”
A deep scattering spectrum — Deep Siamese network pipeline for unsupervised acoustic modeling (2016, background): “In addition, experiments and computational models in psycholinguistics have shown that lexical information can help refine phonetic categories [12, 13].”
One shot learning of simple visual concepts (2011, background): “For spoken words, Feldman, Griffiths, and Morgan (2009) proposed that concepts are learned in conjunction with their components parts, and this is also a guiding principle behind the stroke model.”
Discovering linguistic structures in speech: models and applications (2014, background): “/ ae n d/ (and, end, attend) [37] [12 67] 41 /f l ae t/ (flat, flatten) [81] [28 16 21] 39 /ih z/ (this, is, it’s) [47 59] 33 the world [35 40 102] [38 91] 31 /ax bcl ax l/ (able, cable, incredible) [34 18] [38 91] 18 /aw n dh/ (down, how, download) [11] [95 8] 16 /s cl t eh r/ (this era, first era)”
Measuring the perceptual availability of phonological features during language acquisition using unsupervised binary stochastic autoencoders (2019, background): “…emphasized the importance of topdown information (information about the contexts in which phonemes occur) (Peperkamp et al., 2006; Swingley, 2009; Feldman et al., 2009a, 2013a,b; Moreton and Pater, 2012a,b; Martin et al., 2013; Pater and Moreton, 2014; Frank et al., 2014; Doyle et al., 2014;…”