Thomas Merritt

Jaime Lorenzo-Trueba

CoRR, 2023

AE-Flow: Autoencoder Normalizing Flow.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

Expressive, Variable, and Controllable Duration Modelling in TTS.

[BibT_eX]

[DOI]

CoRR, 2022

Text-free non-parallel many-to-many voice conversion using normalising flows.

[BibT_eX]

[DOI]

CoRR, 2022

Remap, Warp and Attend: Non-Parallel Many-to-Many Accent Conversion with Normalizing Flows.

[BibT_eX]

[DOI]

Proceedings of the IEEE Spoken Language Technology Workshop, 2022

GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion.

[BibT_eX]

[DOI]

Magdalena Proszewska

Grzegorz Beringer

Daniel Sáez-Trigueros

Abdelhamid Ezzerg

Proceedings of the Interspeech 2022, 2022

Creating New Voices using Normalizing Flows.

[BibT_eX]

[DOI]

Proceedings of the Interspeech 2022, 2022

Expressive, Variable, and Controllable Duration Modelling in TTS.

[BibT_eX]

[DOI]

Proceedings of the Interspeech 2022, 2022

Text-Free Non-Parallel Many-To-Many Voice Conversion Using Normalising Flow.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2022

2021

Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech.

[BibT_eX]

[DOI]

CoRR, 2021

Low-Resource Expressive Text-To-Speech Using Data Augmentation.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

Camp: A Two-Stage Approach to Modelling Prosody in Context.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

Parallel WaveNet conditioned on VAE latent vectors.

[BibT_eX]

[DOI]

CoRR, 2020

2019

In Other News: a Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited Data.

[BibT_eX]

[DOI]

Nishant Prateek

Mateusz Lajszczak

Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019

Towards Achieving Robust Universal Neural Vocoding.

[BibT_eX]

[DOI]

Alexis Moinet

Vatsal Aggarwal

Proceedings of the Interspeech 2019, 2019

Effect of Data Reduction on Sequence-to-sequence Neural TTS.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2019

2018

Effect of data reduction on sequence-to-sequence neural TTS.

[BibT_eX]

[DOI]

CoRR, 2018

Robust universal neural vocoding.

[BibT_eX]

[DOI]

CoRR, 2018

Analysing Shortcomings of Statistical Parametric Speech Synthesis.

[BibT_eX]

[DOI]

CoRR, 2018

Comprehensive Evaluation of Statistical Speech Waveform Synthesis.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

2017

Overcoming the limitations of statistical parametric speech synthesis.

[BibT_eX]

[DOI]

PhD thesis, 2017

Phrase Break Prediction for Long-Form Reading TTS: Exploiting Text Structure Information.

[BibT_eX]

[DOI]

Thomas Drugman

Proceedings of the Interspeech 2017, 2017

2016

From HMMS to DNNS: Where do the improvements come from?

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Deep neural network-guided unit selection synthesis.

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

Deep neural network context embeddings for model selection in rich-context HMM synthesis.

[BibT_eX]

[DOI]

Proceedings of the INTERSPEECH 2015, 2015

Attributing modelling errors in HMM synthesis by stepping gradually from natural to modelled speech.

[BibT_eX]

[DOI]

Javier Latorre

Simon King

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

2014

Investigating source and filter contributions, and their interaction, to statistical parametric speech synthesis.

[BibT_eX]

[DOI]

Tuomo Raitio

Simon King

Proceedings of the INTERSPEECH 2014, 2014

Measuring the perceptual effects of modelling assumptions in speech synthesis using stimuli constructed from repeated natural speech.

[BibT_eX]

[DOI]

Proceedings of the INTERSPEECH 2014, 2014

A flexible front-end for HTS.

[BibT_eX]

[DOI]

Proceedings of the INTERSPEECH 2014, 2014

2013

Investigating the shortcomings of HMM synthesis.

[BibT_eX]

[DOI]