Vocal imitation in sensorimotor learning models: a comparative review

S Pagliarini, A Leblois, X Hinaut - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Sensorimotor learning represents a challenging problem for natural and artificial systems.
Several computational models have been proposed to explain the neural and cognitive …

[HTML][HTML] Simulating vocal learning of spoken language: Beyond imitation

DR van Niekerk, A Xu, B Gerazov, PK Krug… - Speech …, 2023 - Elsevier
Computational approaches have an important role to play in understanding the complex
process of speech acquisition, in general, and have recently been popular in studies of …

Learning to produce syllabic speech sounds via reward-modulated neural plasticity

AS Warlaumont, MK Finnegan - PloS one, 2016 - journals.plos.org
At around 7 months of age, human infants begin to reliably produce well-formed syllables
containing both consonants and vowels, a behavior called canonical babbling. Over …

Decode, Move and Speak! Self-supervised Learning of Speech Units, Gestures, and Sound Relationships Using Vocal Imitation

MA Georges, M Lavechin, JL Schwartz… - Computational …, 2024 - direct.mit.edu
Speech learning encompasses mastering a complex motor system to produce speech
sounds from articulatory gestures while simultaneously uncovering discrete units that …

Goal-directed exploration for learning vowels and syllables: a computational model of speech acquisition

A Philippsen - KI-Künstliche Intelligenz, 2021 - Springer
Infants learn to speak rapidly during their first years of life, gradually improving from simple
vowel-like sounds to larger consonant-vowel complexes. Learning to control their vocal tract …

Articulatory Copy Synthesis Based on the Speech Synthesizer VocalTractLab and Convolutional Recurrent Neural Networks

Y Gao, P Birkholz, Y Li - IEEE/ACM Transactions on Audio …, 2024 - ieeexplore.ieee.org
Articulatory copy synthesis (ACS) refers to the synthetic reproduction of natural utterances.
The existing methods of ACS have the limitations of poor generalizability for unknown …

Seeing [u] aids vocal learning: Babbling and imitation of vowels using a 3D vocal tract model, reinforcement learning, and reservoir computing

M Murakami, B Kröger, P Birkholz… - 2015 joint IEEE …, 2015 - ieeexplore.ieee.org
We present a model of imitative vocal learning consisting of two stages. First, the infant is
exposed to the ambient language and forms auditory knowledge of the speech items to be …

Artificial vocal learning guided by phoneme recognition and visual information

PK Krug, P Birkholz, B Gerazov… - … on Audio, Speech …, 2023 - ieeexplore.ieee.org
This paper introduces a paradigm shift regarding vocal learning simulations, in which the
communicative function of speech acquisition determines the learning process and …

A predictive coding framework for a developmental agent: Speech motor skill acquisition and speech production

S Najnin, B Banerjee - Speech Communication, 2017 - Elsevier
Predictive coding has been hypothesized as a universal principle guiding the operation in
different brain areas. In this paper, a predictive coding framework for a developmental agent …

[HTML][HTML] Artificial vocal learning guided by speech recognition: What it may tell us about how children learn to speak

A Xu, DR Van Niekerk, B Gerazov, PK Krug… - Journal of …, 2024 - Elsevier
It has long been a mystery how children learn to speak without formal instructions. Previous
research has used computational modelling to help solve the mystery by simulating vocal …