• Refine your search:
  • 
    Keyword:
    
    • [SCCO.LING]Cognitive science / Linguistics (3)
    • [SCCO]Cognitive science (3)
    • Language acquisition (2)
    • [INFO.INFO-CL]Computer Science [cs] / Computation and Language [cs.CL] (2)
    • ABX (1)
    • Artificial intelligence (1)
    • Child activity corpus (1)
    • Child speech corpus (1)
    • Cognitive development (1)
    • Computational modeling (1)
    •   more
  • 
    Creator / Publisher:
    
    • Apprentissage machine et développement cognitif (CoML) (3)
    • Dupoux, Emmanuel (3)
    • Département d'Etudes Cognitives - ENS Paris (DEC) (3)
    • Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria) (3)
    • Laboratoire de sciences cognitives et psycholinguistique (LSCP) (3)
    • Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-École des hautes études en sciences sociales (EHESS)-Centre National de la Recherche Scientifique (CNRS) (3)
    • Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-École des hautes études en sciences sociales (EHESS)-Centre National de la Recherche Scientifique (CNRS)-Département d'Etudes Cognitives - ENS Paris (DEC) (3)
    • Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-École des hautes études en sciences sociales (EHESS)-Centre National de la Recherche Scientifique (CNRS)-Inria de Paris (3)
    • Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-École normale supérieure - Paris (ENS-PSL) (2)
    • École normale supérieure - Paris (ENS-PSL) (2)
    •   more
  • 
    Year:
    
    • 2018 (3)
  • 
    Medium:
    
    • Online (3)
  • 
    Type
  • 
    BLLDB-Access

Search in the Catalogues and Directories

All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year Sort by creator [A → Z]' creator [Z → A]' publishing year ↑ (asc)' publishing year ↓ (desc)' title [A → Z]' title [Z → A]' Simple Search Hits 1 – 3 of 3 1 Baby Cloud, a technological platform for parents and researchers Cao, Xuan-Nga; Dakhlia, Cyrille; Del Carmen, Patricia... In: LREC 2018 - 11th edition of the Language Resources and Evaluation Conference ; https://hal.archives-ouvertes.fr/hal-01948107 ; LREC 2018 - 11th edition of the Language Resources and Evaluation Conference, May 2018, Miyazaki, Japan (2018) BASE Show details 2 Cognitive science in the era of artificial intelligence: A roadmap for reverse-engineering the infant language-learner Dupoux, Emmanuel In: ISSN: 0010-0277 ; EISSN: 1873-7838 ; Cognition ; https://hal.archives-ouvertes.fr/hal-01888694 ; Cognition, Elsevier, 2018, 173, pp.43 - 59. ⟨10.1016/j.cognition.2017.11.008⟩ (2018) BASE Show details 3 Sampling strategies in Siamese Networks for unsupervised speech representation learning Riad, Rachid; Dancette, Corentin; Karadayi, Julien; Zeghidour, Neil; Schatz, Thomas; Dupoux, Emmanuel In: Interspeech 2018 ; https://hal.archives-ouvertes.fr/hal-01888725 ; Interspeech 2018, Sep 2018, Hyderabad, India (2018) Abstract: Conference paper at Interspeech 2018 ; International audience ; Recent studies have investigated siamese network architectures for learning invariant speech representations using same-different side information at the word level. Here we investigate systematically an often ignored component of siamese networks: the sampling procedure (how pairs of same vs. different tokens are selected). We show that sampling strategies taking into account Zipf's Law, the distribution of speakers and the proportions of same and different pairs of words significantly impact the performance of the network. In particular, we show that word frequency compression improves learning across a large range of variations in number of training pairs. This effect does not apply to the same extent to the fully unsupervised setting, where the pairs of same-different words are obtained by spoken term discovery. We apply these results to pairs of words discovered using an unsupervised algorithm and show an improvement on state-of-the-art in unsupervised representation learning using siamese networks. Keyword: [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [SCCO.LING]Cognitive science/Linguistics; [SCCO]Cognitive science; [STAT.OT]Statistics [stat]/Other Statistics [stat.ML]; ABX; Index Terms: language acquisition; Language acquisition; sam-pling; Sampling; Siamese network; speech embeddings; speech recognition; unsupervised learning; weakly supervised learning; zero re-source speech technology; Zero resource speech technology; Zipf's law; Zipf’s law URL: https://hal.archives-ouvertes.fr/hal-01888725/document https://hal.archives-ouvertes.fr/hal-01888725 https://hal.archives-ouvertes.fr/hal-01888725/file/Riad_DKZSD_2018_Sampling_strategies_for_unsup_siamese.Interspeech.pdf BASE Hide details

Mobile view All Catalogues UB Frankfurt Linguistik 0 IDS Mannheim 0 OLC Linguistik 0 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 0 Institut für Empirische Sprachwissenschaft 0 Leibniz-Centre General Linguistics (ZAS) 0 Bibliographies BLLDB 0 BDSL 0 IDS Bibliografie zur deutschen Grammatik 0 IDS Bibliografie zur Gesprächsforschung 0 IDS Konnektoren im Deutschen 0 IDS Präpositionen im Deutschen 0 IDS OBELEX meta 0 MPI-SHH Linguistics Collection 0 MPI for Psycholinguistics 0 Linked Open Data catalogues Annohub 0 Online resources Link directory 0 Journal directory 0 Database directory 0 Dictionary directory 0 Open access documents BASE 3 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0