Voice Conversion for Whispered Speech Synthesis

Jan 17, 2020
Marius Cotescu, Thomas Drugman, Goeric Huybrechts, Jaime Lorenzo-Trueba, Alexis Moinet

* Submitted to IEEE Signal Processing Letters 

  Access Model/Code and Paper
Dynamic Prosody Generation for Speech Synthesis using Linguistics-Driven Acoustic Embedding Selection

Dec 02, 2019
Shubhi Tyagi, Marco Nicolis, Jonas Rohnke, Thomas Drugman, Jaime Lorenzo-Trueba

* Submitted for ICASSP 2020 

  Access Model/Code and Paper
Using VAEs and Normalizing Flows for One-shot Text-To-Speech Synthesis of Expressive Speech

Nov 28, 2019
Vatsal Aggarwal, Marius Cotescu, Nishant Prateek, Jaime Lorenzo-Trueba, Roberto Barra-Chicote

* Submitted to ICASSP 2020 

  Access Model/Code and Paper
In Other News: A Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited Data

Apr 04, 2019
Nishant Prateek, Mateusz Łajszczak, Roberto Barra-Chicote, Thomas Drugman, Jaime Lorenzo-Trueba, Thomas Merritt, Srikanth Ronanki, Trevor Wood

* Accepted at NAACL-HLT 2019 

  Access Model/Code and Paper
Effect of data reduction on sequence-to-sequence neural TTS

Nov 23, 2018
Javier Latorre, Jakub Lachowicz, Jaime Lorenzo-Trueba, Thomas Merritt, Thomas Drugman, Srikanth Ronanki, Klimkov Viacheslav

* 4 pages, 1 extra for references. Submitted to ICASSP 2019 

  Access Model/Code and Paper
Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis

Sep 09, 2018
Gustav Eje Henter, Jaime Lorenzo-Trueba, Xin Wang, Junichi Yamagishi

* 17 pages, 4 figures 

  Access Model/Code and Paper
A Spoofing Benchmark for the 2018 Voice Conversion Challenge: Leveraging from Spoofing Countermeasures for Speech Artifact Assessment

Sep 04, 2018
Tomi Kinnunen, Jaime Lorenzo-Trueba, Junichi Yamagishi, Tomoki Toda, Daisuke Saito, Fernando Villavicencio, Zhenhua Ling

* Correction (bug fix) of a published ODYSSEY 2018 publication with the same title and author list; more details in footnote in page 1 

  Access Model/Code and Paper
The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods

Apr 12, 2018
Jaime Lorenzo-Trueba, Junichi Yamagishi, Tomoki Toda, Daisuke Saito, Fernando Villavicencio, Tomi Kinnunen, Zhenhua Ling

* Accepted for Speaker Odyssey 2018 

  Access Model/Code and Paper
A comparison of recent waveform generation and acoustic modeling methods for neural-network-based speech synthesis

Apr 07, 2018
Xin Wang, Jaime Lorenzo-Trueba, Shinji Takaki, Lauri Juvela, Junichi Yamagishi

* To appear in ICASSP 2018 

  Access Model/Code and Paper
High-quality nonparallel voice conversion based on cycle-consistent adversarial network

Apr 02, 2018
Fuming Fang, Junichi Yamagishi, Isao Echizen, Jaime Lorenzo-Trueba

* accepted at ICASSP 2018 

  Access Model/Code and Paper
Can we steal your vocal identity from the Internet?: Initial investigation of cloning Obama's voice using GAN, WaveNet and low-quality found data

Mar 02, 2018
Jaime Lorenzo-Trueba, Fuming Fang, Xin Wang, Isao Echizen, Junichi Yamagishi, Tomi Kinnunen

* conference manuscript submitted to Speaker Odyssey 2018 

  Access Model/Code and Paper