Article

A mixed generative model of auditory word repetition

2022-01-21

Abstract excerpt

In this paper, we introduce a word repetition generative model (WORM), which—when combined with an appropriate belief updating scheme—is capable of inferring the word that should be spoken when presented with an auditory cue. Our generative model takes a deep temporal form, combining both discrete and continuous states. This allows a (synthetic) WORM agent to perform categorical inference on continuous acoustic si...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 5d99157d-bbe1-563b-a086-b88704002751
DOI: 10.1101/2022.01.20.477138

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

A mixed generative model of auditory word repetitionDOI 10.1101/2022.01.20.477138Read

Repeated imitation makes human vocalizations more word-likeSemantic proximity Read

Exploring Abstract Pattern Representation in The Brain and Non-symbolic Neural NetworksSemantic proximity Read

Listening with generative modelsSemantic proximity Read

Active inference, selective attention, and the cocktail party problemSemantic proximity Read

Sensory context as a universal principle of language in humans and LLMsSemantic proximity Read

Stateful Continuous Thinking: Emergent Self-Referential Dynamics in Stateful Language ModelsSemantic proximity Read

Language experience shapes predictive coding of rhythmic sound sequencesSemantic proximity Read

A hidden generative rule assembles higher-order vocal structures in orangutansSemantic proximity Read

Sensory context improves language prediction in humans and LLMsSemantic proximity Read

Generative Language Reconstruction from Brain RecordingsSemantic proximity Read

Iconicity and Structure in the Emergence of CombinatorialitySemantic proximity Read

Brain-like dynamics in speech representations can emerge through self-supervised learningSemantic proximity Read