2 |
Automatic Normalisation of Early Modern French
|
|
|
|
In: https://hal.inria.fr/hal-03540226 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
3 |
[Rezension zu:] Grund und Grenze des Verstehens : Theologie und Hermeneutik im Anschluss an Friedrich Schleiermacher / Florian Priesemuth. - Berlin: De Gruyter, 2020 (Schleiermacher-Archiv ; 32)
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Aus der Editionswerkstatt: Schleiermachers Praktische Theologie – Frerichs’ Ausgabe in ihre Quellen zerlegt
|
|
|
|
BASE
|
|
Show details
|
|
5 |
From FreEM to D'AlemBERT ; From FreEM to D'AlemBERT: a Large Corpus and a Language Model for Early Modern French
|
|
|
|
In: Proceedings of the 13th Language Resources and Evaluation Conference ; https://hal.inria.fr/hal-03596653 ; Proceedings of the 13th Language Resources and Evaluation Conference, European Language Resources Association, Jun 2022, Marseille, France (2022)
|
|
BASE
|
|
Show details
|
|
6 |
Etude de cas de pathologies de la parole dans le cadre de la prise en charge orthophonique
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03568182 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
7 |
The sociative/benefactive applicative construction and the introduction of attitude holders in Tibetan
|
|
|
|
In: Applicative Morphology: Neglected Syntactic and Non-Syntactic Functions ; https://hal.archives-ouvertes.fr/hal-03610908 ; Applicative Morphology: Neglected Syntactic and Non-Syntactic Functions, In press (2022)
|
|
BASE
|
|
Show details
|
|
8 |
Learning and controlling the source-filter representation of speech with a variational autoencoder
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03650569 ; 2022 (2022)
|
|
Abstract:
17 pages, 4 figures, companion website: https://samsad35.github.io/site-sfvae/ ; Understanding and controlling latent representations in deep generative models is a challenging yet important problem for analyzing, transforming and generating various types of data. In speech processing, inspiring from the anatomical mechanisms of phonation, the source-filter model considers that speech signals are produced from a few independent and physically meaningful continuous latent factors, among which the fundamental frequency f0 and the formants are of primary importance. In this work, we show that the source-filter model of speech production naturally arises in the latent space of a variational autoencoder (VAE) trained in an unsupervised manner on a dataset of natural speech signals. Using only a few seconds of labeled speech signals generated with an artificial speech synthesizer, we experimentally illustrate that f0 and the formant frequencies are encoded in orthogonal subspaces of the VAE latent space and we develop a weakly-supervised method to accurately and independently control these speech factors of variation within the learned latent subspaces. Without requiring additional information such as text or human-labeled data, this results in a deep generative model of speech spectrograms that is conditioned on f0 and the formant frequencies, and which is applied to the transformation of speech signals.
|
|
Keyword:
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD]; Deep generative models; Representation learning; Source-filter model; Variational autoencoder
|
|
URL: https://hal.archives-ouvertes.fr/hal-03650569 https://hal.archives-ouvertes.fr/hal-03650569/document https://hal.archives-ouvertes.fr/hal-03650569/file/sadok2022learning.pdf
|
|
BASE
|
|
Hide details
|
|
9 |
Introducing the HIPE 2022 Shared Task: Named Entity Recognition and Linking in Multilingual Historical Documents
|
|
|
|
In: Advances in Information Retrieval. 44th European Conference on IR Research, ECIR 2022, Stavanger, Norway, April 10–14, 2022, Proceedings, Part II ; https://hal.archives-ouvertes.fr/hal-03635971 ; Matthias Hagen; Suzan Verberne; Craig Macdonald; Christin Seifert; Krisztian Balog; Kjetil Nørvåg; Vinay Setty. Advances in Information Retrieval. 44th European Conference on IR Research, ECIR 2022, Stavanger, Norway, April 10–14, 2022, Proceedings, Part II, 13186, Springer International Publishing, pp.347-354, 2022, Lecture Notes in Computer Science, 978-3-030-99738-0. ⟨10.1007/978-3-030-99739-7_44⟩ (2022)
|
|
BASE
|
|
Show details
|
|
10 |
Le tibétain parlé : exercices pratiques (vol. 1)
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03610669 ; A paraître (2022)
|
|
BASE
|
|
Show details
|
|
11 |
The grammaticalization of plurality in the languages of Amdo
|
|
|
|
In: Himalayan Linguistics ; https://hal.archives-ouvertes.fr/hal-03610576 ; Himalayan Linguistics, 2022, 20 (3), ⟨10.5070/H920353650⟩ (2022)
|
|
BASE
|
|
Show details
|
|
12 |
Replication data and results for the publication "The dirty work of boundary maintenance" ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Grenzüberschreitendes Textmining von Historischen Zeitungen - Das impresso-Projekt zwischen Text- und Bildverarbeitung, Design und Geschichtswissenschaft ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Grenzüberschreitendes Textmining von Historischen Zeitungen - Das impresso-Projekt zwischen Text- und Bildverarbeitung, Design und Geschichtswissenschaft ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Consent to Research in Madagascar: Challenges, Strategies, and Priorities for Future Research
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Utilising a systematic review-based approach to create a database of individual participant data for meta- and network meta-analyses: The RELEASE database of aphasia after stroke
|
|
|
|
In: Research outputs 2014 to 2021 (2022)
|
|
BASE
|
|
Show details
|
|
|
|