ProfessorsProfessors of University of CreteDipjyoti Paul, PhD

Dipjyoti Paul, PhD

University of Crete

H-index: 9

Europe-Greece

About Dipjyoti Paul, PhD

Dipjyoti Paul, PhD, With an exceptional h-index of 9 and a recent h-index of 9 (since 2020), a distinguished researcher at University of Crete, specializes in the field of Machine learning, Deep Learning, Generative Networks, Speech Synthesis, Spoofing Countermeasure.

His recent articles reflect a diverse array of research interests and contributions to the field:

Multi-MelGAN voice conversion for the creation of under-resourced child speech synthesis

Cumulant gan

A Variance Reduction Method for Neural-based Divergence Estimation

A Universal Multi-Speaker Multi-Style Text-to-Speech via Disentangled Representation Learning Based on Rényi Divergence Minimization

Speech Frame Selection for Spoofing Detection with an Application to Partially Spoofed Audio-Data

Enhancing Speech Intelligibility in Text-To-Speech Synthesis using Speaking Style Conversion

Speaker Conditional WaveRNN: Towards Universal Neural Vocoder for Unseen Speaker and Recording Conditions

Dipjyoti Paul, PhD Information

University	University of Crete
Position	PhD student Marie Curie Fellow Computer Science Department
Citations(all)	416
Citations(since 2020)	344
Cited By	187
hIndex(all)	9
hIndex(since 2020)	9
i10Index(all)	9
i10Index(since 2020)	8
Email	Access Email
University Profile Page	University of Crete
Google Scholar	View Google Scholar Profile

Dipjyoti Paul, PhD Skills & Research Interests

Machine learning

Deep Learning

Generative Networks

Speech Synthesis

Spoofing Countermeasure

Top articles of Dipjyoti Paul, PhD

Title	Journal	Author(s)	Publication Date
Multi-MelGAN voice conversion for the creation of under-resourced child speech synthesis		Avashna Govender Dipjyoti Paul	2022/5/16
Cumulant gan	IEEE Transactions on Neural Networks and Learning Systems	Yannis Pantazis Dipjyoti Paul Michail Fasoulakis Yannis Stylianou Markos A Katsoulakis	2022/4/6
A Variance Reduction Method for Neural-based Divergence Estimation		Jeremiah Birrell Markos A Katsoulakis Yannis Pantazis Dipjyoti Paul Anastasios Tsourtis	2021/10/6
A Universal Multi-Speaker Multi-Style Text-to-Speech via Disentangled Representation Learning Based on Rényi Divergence Minimization	Proc. Interspeech 2021	Dipjyoti Paul Sankar Mukherjee Yannis Pantazis Yannis Stylianou	2021
Speech Frame Selection for Spoofing Detection with an Application to Partially Spoofed Audio-Data	International Journal of Speech Technology	A Kishore Kumar Dipjyoti Paul Monisankha Pal Md Sahidullah Goutam Saha	2021/3
Enhancing Speech Intelligibility in Text-To-Speech Synthesis using Speaking Style Conversion	Proc. Interspeech 2020	Dipjyoti Paul Muhammed PV Shifas Yannis Pantazis Yannis Stylianou	2020
Speaker Conditional WaveRNN: Towards Universal Neural Vocoder for Unseen Speaker and Recording Conditions		Dipjyoti Paul Yannis Pantazis Yannis Stylianou	2020/8/9