Can phones, syllables, and words emerge as side-products of cross-situational audiovisual learning? -- A computational investigation

arXiv:2109.14200v2 Announce Type: replace-cross
Abstract: Decades of research has studied how language learning infants learn to discriminate speech sounds, segment words, and associate words with their meanings. While gradual development of such capabilities is unquestionable, the exact nature of these skills and the underlying mental representations yet remains unclear. In parallel, computational studies have shown that basic comprehension of speech can be achieved by statistical learning between speech and concurrent referentially ambiguous visual input. These models can operate without prior …

abstract arxiv capabilities computational cs.ai cs.cl cs.cv cs.lg cs.sd development eess.as investigation language learn nature phones products research segment skills speech type words