Подписаться
Viet Anh TRAN
Viet Anh TRAN
Deezer Research
Подтвержден адрес электронной почты в домене deezer.com
Название
Процитировано
Процитировано
Год
Gravity-inspired graph autoencoders for directed link prediction
G Salha, S Limnios, R Hennequin, VA Tran, M Vazirgiannis
Proceedings of the 28th ACM international conference on information and …, 2019
1132019
Improvement to a NAM-captured whisper-to-speech system
VA Tran, G Bailly, H Lœvenbruck, T Toda
Speech communication 52 (4), 314-326, 2010
812010
A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps
L Briand, G Salha-Galvan, W Bendada, M Morlon, VA Tran
27th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2021
472021
A Degeneracy Framework for Scalable Graph Autoencoders
G Salha, R Hennequin, VA Tran, M Vazirgiannis
IJCAI, 2019
442019
Comparing multi-stage approaches for cross-show speaker diarization
VA Tran, VB Le, C Barras, L Lamel
Interspeech 2011, 2011
432011
Analysis and recognition of NAM speech using HMM distances and visual information
P Heracleous, VA Tran, T Nagai, K Shikano
IEEE transactions on Audio, speech, and language processing 18 (6), 1528-1538, 2009
382009
Improving Collaborative Metric Learning by Efficient Negative Sampling
VA Tran, R Hennequin, J Royo-Letelier, M Moussallam
SIGIR, 1201-1204, 2019
302019
Improving transformers with probabilistic attention keys
TM Nguyen, TM Nguyen, DDD Le, DK Nguyen, VA Tran, R Baraniuk, ...
International Conference on Machine Learning, 16595-16621, 2022
252022
Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders
G Salha-Galvan, R Hennequin, B Chapus, VA Tran, M Vazirgiannis
15th ACM Conference on Recommender Systems, 2021
232021
Attention mixtures for time-aware sequential recommendation
VA Tran, G Salha-Galvan, B Sguerra, R Hennequin
Proceedings of the 46th International ACM SIGIR Conference on Research and …, 2023
202023
Multimodal HMM-based NAM-to-speech conversion
VA Tran, G Bailly, H Loevenbruck, T Toda
182009
Many-to-Many Voice Conversion based Feature Disentanglement using Variational Autoencoder
M Luong, VA Tran
Interspeech, 2021
162021
Discovery dynamics: Leveraging repeated exposure for user and music characterization
B Sguerra, VA Tran, R Hennequin
Proceedings of the 16th ACM Conference on Recommender Systems, 556-561, 2022
112022
Hierarchical Latent Relation Modeling for Collaborative Metric Learning
VA Tran, G Salha-Galvan, R Hennequin, M Moussallam
15th ACM Conference on Recommender Systems, 2021
112021
Disambiguating music artists at scale with audio metric learning
J Royo-Letelier, R Hennequin, VA Tran, M Moussallam
arXiv preprint arXiv:1810.01807, 2018
112018
Predicting F0 and voicing from NAM-captured whispered speech
VA Tran, G Bailly, H Loevenbruck, T Toda
Speech Prosody 2008-4th International Conference on Speech Prosody, 107-110, 2008
112008
Personalized breath based biometric authentication with wearable multimodality
MH Bui, VA Tran, C Pham
arXiv preprint arXiv:2110.15941, 2021
72021
Ex2vec: Characterizing users and items from the mere exposure effect
B Sguerra, VA Tran, R Hennequin
Proceedings of the 17th ACM Conference on Recommender Systems, 971-977, 2023
62023
Personalized breath-based biometric authentication with wearable multimodality
C Pham, MH Bui, VA Tran, AD Vu, C Tran
IEEE Sensors Journal 23 (1), 536-543, 2022
62022
FlowVocoder: A small footprint neural vocoder based normalizing flow for speech synthesis
M Luong, VA Tran
arXiv preprint arXiv:2109.13675, 2021
52021
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–20