@inproceedings{lavechin-hueber-2025-perception,
title = "From perception to production: how acoustic invariance facilitates articulatory learning in a self-supervised vocal imitation model",
author = "Lavechin, Marvin and
Hueber, Thomas",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1217/",
pages = "23863--23874",
ISBN = "979-8-89176-332-6",
abstract = "Human infants face a formidable challenge in speech acquisition: mapping extremely variable acoustic inputs into appropriate articulatory movements without explicit instruction. We present a computational model that addresses the acoustic-to-articulatory mapping problem through self-supervised learning. Our model comprises a feature extractor that transforms speech into latent representations, an inverse model that maps these representations to articulatory parameters, and a synthesizer that generates speech outputs. Experiments conducted in both single- and multi-speaker settings reveal that intermediate layers of a pre-trained wav2vec 2.0 model provide optimal representations for articulatory learning, significantly outperforming MFCC features. These representations enable our model to learn articulatory trajectories that correlate with human patterns, discriminate between places of articulation, and produce intelligible speech. Critical to successful articulatory learning are representations that balance phonetic discriminability with speaker invariance {--} precisely the characteristics of self-supervised representation learning models. Our findings provide computational evidence consistent with developmental theories proposing that perceptual learning of phonetic categories guides articulatory development, offering insights into how infants might acquire speech production capabilities despite the complex mapping problem they face."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lavechin-hueber-2025-perception">
<titleInfo>
<title>From perception to production: how acoustic invariance facilitates articulatory learning in a self-supervised vocal imitation model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marvin</namePart>
<namePart type="family">Lavechin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Hueber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Human infants face a formidable challenge in speech acquisition: mapping extremely variable acoustic inputs into appropriate articulatory movements without explicit instruction. We present a computational model that addresses the acoustic-to-articulatory mapping problem through self-supervised learning. Our model comprises a feature extractor that transforms speech into latent representations, an inverse model that maps these representations to articulatory parameters, and a synthesizer that generates speech outputs. Experiments conducted in both single- and multi-speaker settings reveal that intermediate layers of a pre-trained wav2vec 2.0 model provide optimal representations for articulatory learning, significantly outperforming MFCC features. These representations enable our model to learn articulatory trajectories that correlate with human patterns, discriminate between places of articulation, and produce intelligible speech. Critical to successful articulatory learning are representations that balance phonetic discriminability with speaker invariance – precisely the characteristics of self-supervised representation learning models. Our findings provide computational evidence consistent with developmental theories proposing that perceptual learning of phonetic categories guides articulatory development, offering insights into how infants might acquire speech production capabilities despite the complex mapping problem they face.</abstract>
<identifier type="citekey">lavechin-hueber-2025-perception</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1217/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>23863</start>
<end>23874</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From perception to production: how acoustic invariance facilitates articulatory learning in a self-supervised vocal imitation model
%A Lavechin, Marvin
%A Hueber, Thomas
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F lavechin-hueber-2025-perception
%X Human infants face a formidable challenge in speech acquisition: mapping extremely variable acoustic inputs into appropriate articulatory movements without explicit instruction. We present a computational model that addresses the acoustic-to-articulatory mapping problem through self-supervised learning. Our model comprises a feature extractor that transforms speech into latent representations, an inverse model that maps these representations to articulatory parameters, and a synthesizer that generates speech outputs. Experiments conducted in both single- and multi-speaker settings reveal that intermediate layers of a pre-trained wav2vec 2.0 model provide optimal representations for articulatory learning, significantly outperforming MFCC features. These representations enable our model to learn articulatory trajectories that correlate with human patterns, discriminate between places of articulation, and produce intelligible speech. Critical to successful articulatory learning are representations that balance phonetic discriminability with speaker invariance – precisely the characteristics of self-supervised representation learning models. Our findings provide computational evidence consistent with developmental theories proposing that perceptual learning of phonetic categories guides articulatory development, offering insights into how infants might acquire speech production capabilities despite the complex mapping problem they face.
%U https://aclanthology.org/2025.emnlp-main.1217/
%P 23863-23874
Markdown (Informal)
[From perception to production: how acoustic invariance facilitates articulatory learning in a self-supervised vocal imitation model](https://aclanthology.org/2025.emnlp-main.1217/) (Lavechin & Hueber, EMNLP 2025)
ACL