Titouan Parcollet

Titouan Parcollet

Auto-generated profile, based on publicly available information

Titouan Parcollet

Avignon Université LIA France

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 August 2019 in Artificial Intelligence Review
Verified
Journal Article
Closed access
PDF file
TPTitouan Parcollet
Titouan Parcollet
MMMohamed Morchid
Mohamed Morchid
GLGeorges Linarès
Georges Linarès

3 February 2024 in Computer Speech & Language
Verified
Journal Article
Open access
TPTitouan Parcollet
Titouan Parcollet
HNHa Nguyen
Ha Nguyen
SESolène Evain
Solène Evain
MBMarcely Zanon Boito
Marcely Zanon Boito
APAdrien Pupier
Adrien Pupier
LBLaurent Besacier
Laurent Besacier

1 December 2017
Verified
Conference Paper
Open access
TPTitouan Parcollet
Titouan Parcollet
MMMohamed Morchid
Mohamed Morchid
GLGeorges Linares
Georges Linares
Deep Neural Networks (DNN) received a great interest from researchers due to their capability to construct robust abstract representations of heterogeneous documents in a latent subspace. Nonetheless, mere real-valued deep neural networks require an appropriate adaptation, such as the convolution process, to capture latent relations between input features. Moreover, real-valued deep neural networks reveal little in way of document internal dependencies, by only considering words or topics contained in the document as an isolate basic element. Quaternion-valued multi-layer perceptrons (QMLP), and autoencoders (QAE) have been introduced to capture such latent dependencies, alongside to represent multidimensional data. Nonetheless, a three-layered neural network does not benefit from the high abstraction capability of DNNs. The paper proposes first to extend the hyper-complex algebra to deep neural networks (QDNN) and, then, introduces pre-trained deep quaternion neural networks (QDNN-AE) with dedicated quaternion encoder-decoders (QAE). The experiments conduced on a theme identification task of spoken dialogues from the DECODA data set show, inter alia, that the QDNN-AE reaches a promising gain of 2.2% compared to the standard real-valued DNN-AE.

20 August 2023
Verified
Conference Paper
Open access
FMFlorian Mai
Florian Mai
JGJuan Pablo Zuluaga Gomez
Juan Pablo Zuluaga Gomez
TPTitouan Parcollet
Titouan Parcollet
PMPetr Motlicek
Petr Motlicek

31 October 2019 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
TPTitouan Parcollet
Titouan Parcollet
MMMohamed Morchid
Mohamed Morchid
XBXavier Bost
Xavier Bost
GLGeorges Linares
Georges Linares
RMRenato De Mori
Renato De Mori
Machine learning (ML) and deep learning with deep neural networks (DNN), have drastically improved the performances of modern systems on numerous spoken language understanding (SLU) related tasks. Since most of current researches focus on new neural architectures to enhance the performances in realistic conditions, few recent works investigated the use of different algebras with neural networks (NN), to better represent the nature of the data being processed. To this extent, quaternion-valued neural networks (QNN) have shown better performances, and an important reduction of the number of neural parameters compared to traditional real-valued neural networks, when dealing with multidimensional signal. Nonetheless, the use of QNNs is strictly limited to quaternion input or output features. This paper introduces a new unsupervised method based on a hybrid autoencoder (AE) called real-to-quaternion autoencoder (R2H), to extract a quaternion-valued input signal from any real-valued data, to be processed by QNNs. The experiments performed to identify the most related theme of a given telephone conversation from a customer care service (CCS), demonstrate that the R2H approach outperforms all the previously established models, either real- or quaternion-valued ones, in term of accuracy and with up to four times fewer neural parameters.

7 April 2021 in arXiv
Verified
Preprint
Open access
PDF file
AMAkhil Mathur
Akhil Mathur
DBDaniel J. Beutel
Daniel J. Beutel
PGPedro Porto Buarque de Gusmão
Pedro Porto Buarque de Gusmão
JFJavier Fernandez-Marques
Javier Fernandez-Marques
TTTaner Topal
Taner Topal
NLNicholas Lane
Nicholas Lane
Federated Learning (FL) allows edge devices to collaboratively learn a shared prediction model while keeping their training data on the device, thereby decoupling the ability to do machine learning from the need to store data in the cloud. Despite the algorithmic advancements in FL, the support for on-device training of FL algorithms on edge devices remains poor. In this paper, we present an exploration of on-device FL on various smartphones and embedded devices using the Flower framework. We also evaluate the system costs of on-device FL and discuss how this quantification could be used to design more efficient FL algorithms.