1 |
How much does prosody help word segmentation? A simulation study on infant-directed speech
|
|
|
|
In: ISSN: 0010-0277 ; EISSN: 1873-7838 ; Cognition ; https://hal.archives-ouvertes.fr/hal-03498888 ; Cognition, Elsevier, 2022, 219, pp.104961. ⟨10.1016/j.cognition.2021.104961⟩ (2022)
|
|
BASE
|
|
Show details
|
|
2 |
On the role of population heterogeneity in emergent communication ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
SCALa: A blueprint for computational models of language acquisition in social context
|
|
|
|
In: ISSN: 0010-0277 ; EISSN: 1873-7838 ; Cognition ; https://hal.inria.fr/hal-03373586 ; Cognition, Elsevier, 2021, 213, pp.104779. ⟨10.1016/j.cognition.2021.104779⟩ (2021)
|
|
BASE
|
|
Show details
|
|
4 |
The Zero Resource Speech Challenge 2021: Spoken language modelling
|
|
|
|
In: ISSN: 0162-8828 ; IEEE Transactions on Pattern Analysis and Machine Intelligence ; https://hal.inria.fr/hal-03329301 ; IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2021, pp.1-1. ⟨10.1109/TPAMI.2021.3083839⟩ (2021)
|
|
BASE
|
|
Show details
|
|
5 |
The Zero Resource Speech Challenge 2021: Spoken language modelling
|
|
|
|
In: Interspeech 2021 - Conference of the International Speech Communication Association ; https://hal.inria.fr/hal-03329301 ; Interspeech 2021 - Conference of the International Speech Communication Association, Aug 2021, Brno, Czech Republic. ⟨10.1109/TPAMI.2021.3083839⟩ (2021)
|
|
BASE
|
|
Show details
|
|
6 |
Do Infants Really Learn Phonetic Categories?
|
|
|
|
In: EISSN: 2470-2986 ; Open Mind ; https://hal.archives-ouvertes.fr/hal-03550830 ; Open Mind, MIT Press, 2021, 5, pp.113-131. ⟨10.1162/opmi_a_00046⟩ (2021)
|
|
BASE
|
|
Show details
|
|
7 |
Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
|
|
|
|
In: INTERSPEECH 2021 - Annual Conference of the International Speech Communication Association ; https://hal.inria.fr/hal-03329245 ; INTERSPEECH 2021 - Annual Conference of the International Speech Communication Association, Aug 2021, Brno, Czech Republic (2021)
|
|
BASE
|
|
Show details
|
|
8 |
Communicating artificial neural networks develop efficient color-naming systems
|
|
|
|
In: ISSN: 0027-8424 ; EISSN: 1091-6490 ; Proceedings of the National Academy of Sciences of the United States of America ; https://hal.inria.fr/hal-03329084 ; Proceedings of the National Academy of Sciences of the United States of America , National Academy of Sciences, 2021, 118 (12), ⟨10.1073/pnas.2016569118⟩ (2021)
|
|
BASE
|
|
Show details
|
|
9 |
Early phonetic learning without phonetic categories -- Insights from large-scale simulations on realistic input
|
|
|
|
In: ISSN: 0027-8424 ; EISSN: 1091-6490 ; Proceedings of the National Academy of Sciences of the United States of America ; https://hal.archives-ouvertes.fr/hal-03070566 ; Proceedings of the National Academy of Sciences of the United States of America , National Academy of Sciences, 2021, 118 (7), pp.e2001844118. ⟨10.1073/pnas.2001844118⟩ (2021)
|
|
BASE
|
|
Show details
|
|
10 |
Does infant-directed speech help phonetic learning? A machine learning investigation
|
|
|
|
In: ISSN: 0364-0213 ; EISSN: 1551-6709 ; Cognitive Science ; https://hal.archives-ouvertes.fr/hal-03080098 ; Cognitive Science, Wiley, 2021, 45 (5), ⟨10.1111/cogs.12946⟩ (2021)
|
|
Abstract:
International audience ; A prominent hypothesis holds that by speaking to infants in infant-directed speech (IDS) as opposed to adult-directed speech (ADS), parents help them learn phonetic categories. Specifically, two characteristics of IDS have been claimed to facilitate learning: hyperarticulation, which makes the categories more separable and variability, which makes the generalization more robust. Here, we test the separability and robustness of vowel category learning on acoustic representations of speech uttered by Japanese adults in either ADS, IDS (addressed to 18-24 month olds) or read speech (RS). Separability is determined by means of a distance measure computed between the five short vowel categories of Japanese, while robustness is assessed by testing the ability of six different machine learning algorithms trained to classify vowels to generalize on stimuli spoken by a novel speaker in ADS. Using two different speech representations, we find that hyperarticulated speech, in the case of RS, can yield better separability, and that increased between-speaker variability in ADS, can yield, for some algorithms, more robust categories. However, these conclusions do not apply to IDS, which turned out to yield neither more separable nor more robust categories compared to ADS inputs. We discuss the usefulness of machine learning algorithms run on real data to test hypotheses about the functional role of IDS.
|
|
Keyword:
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; [STAT.ML]Statistics [stat]/Machine Learning [stat.ML]; Adult-directed speech; Hyperarticulation; Infant-directed speech; Phonetic learning; Read speech; Speech variability
|
|
URL: https://doi.org/10.1111/cogs.12946 https://hal.archives-ouvertes.fr/hal-03080098/document https://hal.archives-ouvertes.fr/hal-03080098/file/CognitiveScience.pdf https://hal.archives-ouvertes.fr/hal-03080098
|
|
BASE
|
|
Hide details
|
|
11 |
On Generative Spoken Language Modeling from Raw Audio
|
|
|
|
In: EISSN: 2307-387X ; Transactions of the Association for Computational Linguistics ; https://hal.inria.fr/hal-03329219 ; Transactions of the Association for Computational Linguistics, The MIT Press, 2021 (2021)
|
|
BASE
|
|
Show details
|
|
12 |
VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation
|
|
|
|
In: https://hal.inria.fr/hal-03329290 ; 2021, ⟨10.18653/v1/2021.acl-long.80⟩ (2021)
|
|
BASE
|
|
Show details
|
|
13 |
IntPhys 2019: A Benchmark for Visual Intuitive Physics Understanding
|
|
|
|
In: ISSN: 0162-8828 ; IEEE Transactions on Pattern Analysis and Machine Intelligence ; https://hal.archives-ouvertes.fr/hal-02274273 ; IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2021 (2021)
|
|
BASE
|
|
Show details
|
|
14 |
Occlusion resistant learning of intuitive physics from videos
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03139755 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
15 |
Learning spectro-temporal representations of complex sounds with parameterized neural networks
|
|
|
|
In: ISSN: 0001-4966 ; EISSN: 1520-8524 ; Journal of the Acoustical Society of America ; https://hal.inria.fr/hal-03329261 ; Journal of the Acoustical Society of America, Acoustical Society of America, 2021, 150 (1), pp.353-366. ⟨10.1121/10.0005482⟩ (2021)
|
|
BASE
|
|
Show details
|
|
18 |
VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|