Follow
Dipjyoti Paul, PhD
Dipjyoti Paul, PhD
Other namesদীপজ্যোতি পাল
ML Research Engineer, Apple Inc
Verified email at apple.com - Homepage
Title
Cited by
Cited by
Year
Overview of BTAS 2016 Speaker Anti-spoofing Competition
P Korshunov, S Marcel, H Muckenhirn, AR Gonçalves, AGS Mello, ...
IEEE 8th International Conference on Biometrics Theory, Applications and …, 2016
1032016
Spectral features for synthetic speech detection
D Paul, M Pal, G Saha
IEEE journal of selected topics in signal processing 11 (4), 605-617, 2017
842017
Synthetic speech detection using fundamental frequency variation and spectral features
M Pal, D Paul, G Saha
Computer Speech & Language 48, 31-50, 2018
622018
Generalization of Spoofing Countermeasure: A Case Study with ASVSPOOF 2015 and BTAS 2016 Corpora
D Paul, M Sahidullah, G Saha
Proc of IEEE ICASSP, New Orleans, Louisiana, USA, 2017
522017
Speaker Conditional WaveRNN: Towards Universal Neural Vocoder for Unseen Speaker and Recording Conditions
D Paul, Y Pantazis, Y Stylianou
Proc. of INTERSPEECH 2020, 2020
422020
Enhancing Speech Intelligibility in Text-To-Speech Synthesis using Speaking Style Conversion
D Paul, MPV Shifas, Y Pantazis, Y Stylianou
Proc. of INTERSPEECH 2020, 2020
342020
Cumulant gan
Y Pantazis, D Paul, M Fasoulakis, Y Stylianou, MA Katsoulakis
IEEE Transactions on Neural Networks and Learning Systems 34 (11), 9439-9450, 2022
252022
Novel speech features for improved detection of spoofing attacks
D Paul, M Pal, G Saha
Annual IEEE India Conference, INDICON 2015, 1-6, 2016
252016
Acoustic Scene Classification using Block Based MFCC Features
V Ghodasara, S Waldekar, D Paul, G Saha
Detection and Classification of Acoustic Scenes and Events 2016, Budapest …, 2016
172016
Speech Frame Selection for Spoofing Detection with an Application to Partially Spoofed Audio-Data
K Kumar, D Paul, M Pal, M Sahidullah, G Saha
International Journal of Speech Technology, 2021
122021
Non-Parallel Voice Conversion Using Weighted Generative Adversarial Networks
D Paul, Y Pantazis, Y Stylianou
Proc. of INTERSPEECH 2019, 659-663, 2019
82019
Training Generative Adversarial Networks with Weights
Y Pantazis, D Paul, M Fasoulakis, Y Stylianou
European Signal Processing Conference, EUSIPCO 2019, 2019
72019
A Universal Multi-Speaker Multi-Style Text-to-Speech via Disentangled Representation Learning Based on Rényi Divergence Minimization
D Paul, S Mukherjee, Y Pantazis, Y Stylianou
Proc. Interspeech 2021, 3625-3629, 2021
62021
Multi-MelGAN voice conversion for the creation of under-resourced child speech synthesis
A Govender, D Paul
2022 IST-Africa Conference (IST-Africa), 1-6, 2022
22022
Robustness of Voice Conversion Techniques Under Mismatched Conditions
M Pal, D Paul, M Sahidullah, G Saha
arXiv preprint arXiv:1612.07523, 2016
22016
Improving generative adversarial networks and its applications in speech synthesis
D Paul
PhD thesis, 2024
2024
Advancing Speech Accessibility with Personal Voice
D Paul, J Li, L Chang, P Petkov, P Su, S Padinjaru Veettil, Y Tian
https://machinelearning.apple.com/research/personal-voice, 2023
2023
A Variance Reduction Method for Neural-based Divergence Estimation
J Birrell, MA Katsoulakis, Y Pantazis, D Paul, A Tsourtis
2022
Weighted generative adversarial network for many-to-many voice conversion
D Paul, Y Pantazis, Y Stylianou
23rd INTERNATIONAL CONGRESS ON ACOUSTICS (ICA), 659-663, 2019
2019
System and method for automatic synthetic speech detection for speech based biometric authentication
G Saha, D Paul, M Pal
IN Patent 525,491, 2015
2015
The system can't perform the operation now. Try again later.
Articles 1–20