Learning words from sights and sounds: a computational model
Open accessThe DOI matches its Crossref record; 54 of the 54 references it cites were found in a registry or an index.
Abstract
This paper presents an implemented computational model of word acquisition which learns directly from raw multimodal sensory input. Set in an information theoretic framework, the model acquires a lexicon by finding and statistically modeling consistent cross‐modal structure. The model has been implemented in a system using novel speech processing, computer vision, and machine learning algorithms. In evaluations the model successfully performed speech segmentation, word discovery and visual categorization from spontaneous infant‐directed speech paired with video images of single objects. These results demonstrate the possibility of using state‐of‐the‐art techniques from sensory pattern recognition and machine learning to implement cognitive models which can process raw sensor data without the need for human transcription or labeling.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Language development relies on implicit learning of regularities in speech and their pairing with visual cues in the environment.(51–56)”
From Neglect as a violation of species-expectant experience: neurodevelopmental consequences (2017) · cites this paper as [54]
Citations
Cites
Elements of Information Theory
Cover, T. M., & Thomas, J. A. (2001) · Wiley eBooks · doi:10.1002/0471200611 · Cited by 36,808
A tutorial on hidden Markov models and selected applications in speech recognition
Rabiner, L. R. (1989) · Proceedings of the IEEE · doi:10.1109/5.18626 · Cited by 22,743 · cited 2×
“The Forward algorithm (Rabiner, 1989) can be used to compute P(␣ i ͉ j ) and P(␣ j ͉ i ), the probability that the HMM derived from speech segment ␣ i generated speech segment ␣ j and vice versa.”
MethodNeural networks for pattern recognition
(1994) · Choice Reviews Online · doi:10.5860/choice.31-5500 · Cited by 18,538
Neural Networks for Pattern Recognition
Bishop, C. M. (1995) · doi:10.1093/oso/9780198538493.001.0001 · Cited by 12,287
Modeling by shortest data description
Rissanen, J. (1978) · Automatica · doi:10.1016/0005-1098(78)90005-5 · Cited by 6,011
(1960) · Medical Entomology and Zoology · Cited by 5,851
Statistical learning by 8-month-old infants
Saffran, J. R., Aslin, R. N., & Newport, E. L. (1996) · Science · doi:10.1126/science.274.5294.1926 · Cited by 5,659
Harris, Z. S. (1954) · WORD · doi:10.1080/00437956.1954.11659520 · Cited by 4,807
Cognitive representations of semantic categories.
Rosch, E. H. (1975) · Journal of Experimental Psychology General · doi:10.1037//0096-3445.104.3.192 · Cited by 4,756
The CHILDES project: tools for analyzing talk
MacWhinney, B. (1992) · Child Language Teaching and Therapy · doi:10.1177/026565909200800211 · Cited by 3,396
Research works printed but not linked: 5
- Aslin R., 1996, Signal to syntax, 117
- Garofolo J., 1988, Getting started with the DARPA TIMIT CD‐ROM: An acoustic phonetic continuous speech database.
- 10.1037/0096-3445.104.3.192 · doi:10.1037/0096-3445.104.3.192 · Paper page
- Roy D.(1999).Learning words from sights and sounds: A computational model. Unpublished doctoral dissertation Massachusetts Institute of Technology.
- 10.2307/1127555 · doi:10.2307/1127555 · Paper page
Cited by
Items 501–586 of 586
Rouanet, P. (2012) · theses.fr (ABES) · doi:10.70675/0ceedcb7z59b2z4f10zae56z2e46b043cad2 · Cited by 1
Grizou, J. (2014) · theses.fr (ABES) · doi:10.70675/7f2c5210z1859z4befz9622z062070491891 · Cited by 1
Havard, W. N. (2021) · theses.fr (ABES) · doi:10.70675/42e50a10zf9eaz4112zafc5z0b8ce968e31e · Cited by 1
Communicative feedback in language acquisition
Nikolaus, M. (2023) · theses.fr (ABES) · doi:10.70675/342c36b9z6940z46ebz8631ze90a4ba4ae7a · Cited by 1
The language learning infant: Effects of speech input, vocal output, and feedback
Gustavsson, L. (2009) · DiVA (Digitala Vetenskapliga Arkivet)
Wachsmuth, S. (2010) · PUB – Publications at Bielefeld University (Bielefeld University)
Semantic Visual Abstraction for Face Recognition
Cai, Y., Kaufer, D. S., Hart, E., & Solomon, E. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-01970-8_41
Does a synesthetic mechanism aid robot’s language learning?
Nagai, Y. (2006) · PUB – Publications at Bielefeld University (Bielefeld University)
Animate Vision, Virtual Environments, and Neural Codes
Ballard, D. H. (2008) · Elsevier eBooks · doi:10.1016/b978-0-08-046616-3.00008-6
Cai, Y., Milcent, G., & Marian, L. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-89430-8_3
Indexical grounding for a mobile robot
Kehoe, C. W. (2005)
Accessibility of Depicted Events Influences Their Priority in Spoken Comprehension
Crocker, M. W., & Knoeferle, P. (2006) · eScholarship (California Digital Library)
The Influence of Social Priming on Speech Perception
Broussard, S. (2012) · DigitalCommons@Linfield (Linfield College)
Towards natural speech acquisition: incremental word learning with limited data
Clemente, I. A. (2013) · Publikationen an der Universität Bielefeld (Universität Bielefeld)
Efficient setup of acoustic models for large vocabulary continuous speech recognition
Gollan, C., Ney, H., & Lamel, L. F. (2015) · RWTH Publications (RWTH Aachen)
Granting space and time to words: Blind semantic spatial localization for the case of facial images
Mavridis, N., & Bourlai, T. (2014) · International Conference on Robotics and Emerging Allied Technologies in Engineering (iCREATE) · doi:10.1109/icreate.2014.6828352
A special issue on ‘the emergence of language: neural and adaptive agent models’
Cangelosi, A. (2004) · Connection Science · doi:10.1080/09540090412331271432
Okada, S., He, X., Kojima, R., & Hasegawa, O. (2007) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.22.493
Autonomous Learning of Appropriate Social Distance by a Mobile Robot
Wang, Y. (2008) · University of Hertfordshire Research Archive (University of Hertfordshire)
Unsupervised Language Learning for Discovered Visual Concepts
Guha, P., & Mukerjee, A. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37447-0_40
Qu, S., & Chai, J. Y. (2010) · Workshop on Eye Gaze in Intelligent Human Machine Interaction (GazeIn) · doi:10.1145/2002333.2002347
Towards visually-grounded spoken language acquisition
Roy, D. K. (2003) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1109/icmi.2002.1166977
Self-citationMaking Sense of Words through the Eyes of a Child
Gläser, C. (2011)
An approach and experiments with one-class learning*
Lopes, L. S., & Chauhan, A. (2007)
Speech and gesture integration for a game-based command and control environment
Obelnicki, M. C. (2000)
The Emergence of Language in Grounded Adaptive Agents and Robots
Cangelosi, A., Riga, T., Giolito, B., & Marocco, D. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-71009-7_25
Qu, S. (2009) · Michigan State University Libraries · doi:10.25335/m5gm81p3g
Semi-Supervised Learning for Connectionist Networks
Robare, R. J. (2010) · CUNY Academic Works (City University of New York)
Interactive and life-long learning for identification and categorization tasks
Kirstein, S. (2010) · Common Library Network (Der Gemeinsame Bibliotheksverbund)
What is Important for Realizing an Autonomous Interactive Robot?
Komatsu, T., Suzuki, K., Oka, N., Ueda, K., & Hiraki, K. (2002) · The MIT Press eBooks · doi:10.7551/mitpress/3121.003.0073
Building Familiar Attitudes toward Robots through Verb Teaching Interaction
Hasegawa, D., & Araki, K. (2011) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.23.863
Multimodal Joint Attention Based on Mutual Exclusivity Principle
Nakano, T., Yoshikawa, Y., Asada, M., & Ishiguro, H. (2011) · Journal of the Robotics Society of Japan · doi:10.7210/jrsj.27.814
Sasamoto, Y., Yoshikawa, Y., & Asada, M. (2013) · Journal of the Robotics Society of Japan · doi:10.7210/jrsj.31.71
Acquiring and Maintaining Knowledge by Natural Multimodal Dialog
Holzapfel, H. (2009) · Repository KITopen (Karlsruhe Institute of Technology) · doi:10.5445/ir/1000019778
Cross-situational cues are relevant for early word segmentation
Räsänen, O. J., & Rasilo, H. (2015) · eScholarship (California Digital Library)
Possible contributions of simulation and robotics to understanding human language acquisition
Dominey, P. F. (2003) · Cahiers de linguistique française
REFERENTIAL GROUNDING TOWARDS MEDIATING SHARED PERCEPTUAL BASIS IN SITUATED DIALOGUE
Liu, C. (2015) · Michigan State University Libraries · doi:10.25335/m5m11c
Generating a variety of expressions from visual information and user-designated viewpoints
Noguchi, Y., Kondo, M., Kogure, S., Konishi, T., Itoh, Y., Takagi, A., Asoh, H., & Kobayashi, I. (2013) · International Joint Conference on Awareness Science and Technology & Ubi-Media Computing · doi:10.1109/icawst.2013.6765459
A Computational Model of Language Acquisition
ten Bosch, L., Boves, L., & Fikkert, P. (2008)
Experiments with Single-class Support Vector Data Descriptions as a Tool for Vocabulary Grounding
Chauhan, A., & Lopes, L. S. (2010) · Natural Language Processing and Cognitive Science · doi:10.5220/0003028000700078
Image Recognition of an Object Designated by User's Wording
Yamakata, Y. (2006)
第38回研究大会ワークショップ 理論研究再考―理論・モデルは社会言語科学にどう貢献するか?―
正人, 吉., 木本, 幸., 雅史, 岡., & 伸郎, 佐. (2017) · 社会言語科学 · doi:10.19024/jajls.19.2_87
DCG-UPUP-Away : automatic symbol acquisition through grounding to unknowns
Tucker, M. (2016) · DSpace@MIT (Massachusetts Institute of Technology)
Association Learning inspired by the Symbol Grounding Problem
Raue, F. (2018) · Publication Server of Kaiserslautern University of Technology (Kaiserslautern University of Technology)
Development of 3D object’s geometrical properties based architecture for physical symbol grounding
Jayakumar, K. S., & Vimalsamsingh, R. (2019) · AIP conference proceedings · doi:10.1063/1.5127599
Bayesian inference for bilingual word learning
Li, P., Rolotti, S. V., & Zinszer, B. D. (2012)
A Nonlinear Approach to Learning From An Inconsistent Source (with some applications)
Ma, T. (2018) · eScholarship (California Digital Library)
Pre-Training Methods for Vision and Language
Tan, H. (2021) · Carolina Digital Repository (University of North Carolina at Chapel Hill) · doi:10.17615/dk8k-sc87
Ballard, D. H. (2014) · Springer eBooks · doi:10.1007/978-0-387-31439-6_273
Towards Cognitive Machines: Multiscale Measures and Analysis
Kinsner, W. (2010) · Advances in bioinformatics and biomedical engineering book series · doi:10.4018/978-1-61692-004-3.ch004
雄一郎, 吉., & 稔, 浅. (2009) · Journal of the Society of Biomechanisms · doi:10.3951/sobim.33.231
言語とコミュニケーションの創発に関する構成論的研究の展開Preprint
Ueda, R., Taniguchi, T., Suzuki, R., Ebara, H., Nakamura, T., Iwamura, I., & Hashimoto, T. (2023) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/rz5ng
Artificial neural networks to analyze and simulate language acquisition in childrenPreprint
Lavechin, M. (2023) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/5p8ge
(2024) · Tourism social science series · doi:10.1108/s1571-504320240000027032
Allahviranloo, T. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-16147-6.00012-8
[HDR] How AI is Transforming the study of Language DevelopmentPreprint
Fourtassi, A. (2025) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/6hevx
Adaptive Human-Computer Dialogue
Dusan, S., & Flanagan, J. L. (2005) · Text, speech and language technology · doi:10.1007/1-4020-3933-6_15
Analyses of software cognitive complexity supported by an automated parsing tool
Chiew, V. (2012) · Libraries and Cultural Resources (University of Calgary) · doi:10.11575/prism/4962
Darvish, K. (2025) · Maryland Shared Open Access Repository (USMAI Consortium) · doi:10.13016/m2bwgi-sedl
共同注意が不完全なマルチモーダル環境における主観的整合性に基づく対応学習とカテゴリ化
Sasamoto, Y., & 笹本, 勇. (2015) · Institutional Repositories DataBase (IRDB) · doi:10.18910/53992
Learning action models by curiosity driven self exploration and language guided generalization
Panzner, M. (2020) · Publikationen an der Universität Bielefeld (Universität Bielefeld) · doi:10.4119/unibi/2943362
Perceptual symbol grounding through child-like natural language interaction and learning
Perera, I. E., & Allen, J. F. (2016) · UR Research (University of Rochester)
ロボットビジョン応用の展開 : コミュニケーションに関するビジョン
久野, 義., クノ, ヨ., & Kuno, Y. (2006) · Institutional Repositories DataBase (IRDB)
Dinámica temporal de la contribución motora a la categorización de objetos
Perilli, F. G., & Bàsica, E. I. D. L. U. A. D. B. D. D. P. (2016) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)
Unsupervised detection of words - questioning the relevance of segmentation
ten Bosch, L., hamme, H. V., & Boves, L. (2008) · Lirias
Early word learning through communicative inference
Frank, M. C. (2010) · DSpace@MIT (Massachusetts Institute of Technology)
Speech processing with less supervision : learning from weak labels and multiple modalities
Hsu, W.-N. (2020) · DSpace@MIT (Massachusetts Institute of Technology)
マルチモーダル情報を用いた未知物体の認識とグラウンディングに関する研究
小篠, 裕., & オザサ, ユ. (2015) · Institutional Repositories DataBase (IRDB)
Brain-Inspired Audio-Visual Information Processing Using Spiking Neural Networks
Wendt, A. (2021) · Tuwhera (Auckland University of Technology)
Models of semantic representation with visual attribute
Silberer, C., Ferrari, V., & Lapata, M. (2013) · RECERCAT (Consorci de Serveis Universitaris de Catalunya)
Nelson, R. C. (n.d.) · UR Research (University of Rochester)
\nUnsupervised detection of words questioning the relevance of segmentation
ten Bosch, L., Hamme, H. V., & Boves, L. W. J. (2008) · Radboud Repository (Radboud University)
Developmental reasoning and planning with robot through enactive interaction with human
Petit, M. (2014) · theses.fr (ABES) · doi:10.70675/f24c7e09z3756z4f33z90c6z74d9e7cefce0
Interactive learning of words and objects for a humanoid robot
Chen, Y. (2017) · theses.fr (ABES) · doi:10.70675/f966e3c5z3602z4222za6d5zea23372bf41f
Diversity and learnability in early language acquisition : across languages and cultures
Loukatou, G. R. (2020) · theses.fr (ABES) · doi:10.70675/fa251e4dz6435z4676z904bzb030d3647f08
Timing attacks : modelization and protections
Carré, S. (2020) · theses.fr (ABES) · doi:10.70675/ef10712czafd9z4eb1z9775z7f245f8b6bd5
Metonymic Circuits for Abstract Concept Grounding in Vision Transformers
Ding, J., Ma, Z., Mao, J., Chai, J. Y., & Shi, F. (2026) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/2026.emnlp-main.1663
Grounding Language Models at Scale
Ma, M. (2026) · Deep Blue (University of Michigan) · doi:10.7302/dspace/30600
Physical AI: Concepts, Techniques, and ChallengesPreprint
Zhang, W., Shen, C., Xue, T., Zhao, B., Jiang, B., Guo, Z., Cui, Z., Li, Y., Zhou, M., Chen, X., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.27045
Gaspers, J. (2014) · PUB – Publications at Bielefeld University (Bielefeld University)
Metadata
- Authors
- Roy, D. K., & Pentland, A. P.
- Affiliations
- MIT Media Lab (US)
- Corresponding author
- Roy, Deb K.
- Venue
- Cognitive Science
- Publisher
- Wiley
- Published
- 2002-01
- Volume
- 26
- Issue
- 1
- Pages
- 113-146
- ISSN
- 0364-0213 (ISSN-L)
- 1551-6709
- OpenAlex
- W2107917162
- Cited by
- 521
- References
- 51
- Citations by year
- 2025: 1 · 2024: 6 · 2023: 10 · 2022: 13 · 2021: 12 · 2020: 14 · 2019: 18 · 2018: 13 · 2017: 25 · 2016: 25 · 2015: 18 · 2014: 14 · 2013: 24 · 2012: 20
- FWCI
- 59.99
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Cognitive Science (publishedVersion)
- Topics
- Social Sciences › Psychology › Developmental and Educational Psychology › Language Development and Disorders
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Categorization, perception, and language
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Multisensory perception and integration
- Keywords
- vocabulary acquisition, cross-modal correspondence, information theory, speech segmentation, word discovery, visual categorization, infant-directed speech, object recognition, cognitive modeling
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.