1 |
RETRIEVING SPEAKER INFORMATION FROM PERSONALIZED ACOUSTIC MODELS FOR SPEECH RECOGNITION
|
|
|
|
In: IEEE ICASSP 2022 ; https://hal.archives-ouvertes.fr/hal-03539741 ; IEEE ICASSP 2022, 2022, Singapour, Singapore (2022)
|
|
BASE
|
|
Show details
|
|
2 |
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
|
|
3 |
A gentle introduction to Girard's Transcendental Syntax for the linear logician
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-02977750 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
4 |
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
|
|
5 |
Hippocampal ensembles represent sequential relationships among an extended sequence of nonspatial events.
|
|
|
|
In: Nature communications, vol 13, iss 1 (2022)
|
|
BASE
|
|
Show details
|
|
6 |
Changes in the midst of a construction network: a diachronic construction grammar approach to complex prepositions denoting internal location
|
|
|
|
In: ISSN: 0936-5907 ; EISSN: 1613-3641 ; Cognitive Linguistics ; https://halshs.archives-ouvertes.fr/halshs-03637056 ; Cognitive Linguistics, De Gruyter, 2022, ⟨10.1515/cog-2021-0128⟩ (2022)
|
|
BASE
|
|
Show details
|
|
7 |
Changes in the midst of a construction network: a diachronic construction grammar approach to complex prepositions denoting internal location
|
|
|
|
In: ISSN: 0936-5907 ; EISSN: 1613-3641 ; Cognitive Linguistics ; https://halshs.archives-ouvertes.fr/halshs-03637056 ; Cognitive Linguistics, De Gruyter, In press, ⟨10.1515/cog-2021-0128⟩ (2022)
|
|
BASE
|
|
Show details
|
|
8 |
Le modèle Transformer: un « couteau suisse » pour le traitement automatique des langues
|
|
|
|
In: Techniques de l'Ingenieur ; https://hal.archives-ouvertes.fr/hal-03619077 ; Techniques de l'Ingenieur, Techniques de l'ingénieur, 2022, ⟨10.51257/a-v1-in195⟩ ; https://www.techniques-ingenieur.fr/base-documentaire/innovation-th10/innovations-en-electronique-et-tic-42257210/transformer-des-reseaux-de-neurones-pour-le-traitement-automatique-des-langues-in195/ (2022)
|
|
BASE
|
|
Show details
|
|
9 |
Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost
|
|
|
|
In: ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-03613101 ; ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, May 2022, Dublin, Ireland (2022)
|
|
BASE
|
|
Show details
|
|
10 |
Imputing out-of-vocabulary embeddings with LOVE makes language models robust with little cost
|
|
|
|
In: ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-03613101 ; ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, May 2022, Dublin, Ireland (2022)
|
|
BASE
|
|
Show details
|
|
11 |
Structured, flexible, and robust: comparing linguistic plans and explanations generated by humans and large language models ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
From bag-of-words towards natural language: adapting topic models to avoid stop word removal ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
A Collection of Classroom Instruction ... : A Collection of Classroom Instruction ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Biodiversity: how big is our global biodiversity debt and what can we do about it? ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Bayesian data analysis in the phonetic sciences: A tutorial introduction ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
How Cognitive Abilities May Support Children’s Bilingual Literacy Development in a Multilingual Society ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
On the Transferability of Pre-trained Language Models for Low-Resource Programming Languages ...
|
|
Chen, Fuxiang. - : Federated Research Data Repository / dépôt fédéré de données de recherche, 2022
|
|
BASE
|
|
Show details
|
|
|
|