Thomas Merritt

41 papers A 10Misc 8Journal 15Unranked 7

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Voice Conversion for Lombard Speaking Style with Implicit and Explicit Acoustic Feature Conditioning. CoRR Dominika Woszczyk, Manuel Sam Ribeiro, Thomas Merritt, Daniel Korzekwa
2024	—	`conf`	Investigating Self-Supervised Features for Expressive, Multilingual Voice Conversion. ICASSP Workshops Álvaro Martín-Cortinas, Daniel Sáez-Trigueros, Grzegorz Beringer, Iván Vallés-Pérez, Roberto Barra-Chicote, Biel Tura Vecino, Adam Gabrys, Thomas Merritt, Piotr Bilinski, Jaime Lorenzo-Trueba
2023	J	`jnl`	AE-Flow: AutoEncoder Normalizing Flow. CoRR Jakub Mosinski, Piotr Bilinski, Thomas Merritt, Abdelhamid Ezzerg, Daniel Korzekwa
2023	Misc	`conf`	AE-Flow: Autoencoder Normalizing Flow. ICASSP Jakub Mosinski, Piotr Bilinski, Thomas Merritt, Abdelhamid Ezzerg, Daniel Korzekwa
2023	A	`conf`	Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech. INTERSPEECH Guangyan Zhang, Thomas Merritt, Manuel Sam Ribeiro, Biel Tura Vecino, Kayoko Yanagisawa, Kamil Pokora, Abdelhamid Ezzerg, Sebastian Cygert, Ammar Abbas, Piotr Bilinski, Roberto Barra-Chicote, Daniel Korzekwa, Jaime Lorenzo-Trueba
2023	J	`jnl`	Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech. CoRR Guangyan Zhang, Thomas Merritt, Manuel Sam Ribeiro, Biel Tura Vecino, Kayoko Yanagisawa, Kamil Pokora, Abdelhamid Ezzerg, Sebastian Cygert, Ammar Abbas, Piotr Bilinski, Roberto Barra-Chicote, Daniel Korzekwa, Jaime Lorenzo-Trueba
2023	J	`jnl`	Creating New Voices using Normalizing Flows. CoRR Piotr Bilinski, Thomas Merritt, Abdelhamid Ezzerg, Kamil Pokora, Sebastian Cygert, Kayoko Yanagisawa, Roberto Barra-Chicote, Daniel Korzekwa
2022	A	`conf`	Creating New Voices using Normalizing Flows. INTERSPEECH Piotr Bilinski, Thomas Merritt, Abdelhamid Ezzerg, Kamil Pokora, Sebastian Cygert, Kayoko Yanagisawa, Roberto Barra-Chicote, Daniel Korzekwa
2022	A	`conf`	Expressive, Variable, and Controllable Duration Modelling in TTS. INTERSPEECH Syed Ammar Abbas, Thomas Merritt, Alexis Moinet, Sri Karlapati, Ewa Muszynska, Simon Slangen, Elia Gatti, Thomas Drugman
2022	J	`jnl`	Expressive, Variable, and Controllable Duration Modelling in TTS. CoRR Ammar Abbas, Thomas Merritt, Alexis Moinet, Sri Karlapati, Ewa Muszynska, Simon Slangen, Elia Gatti, Thomas Drugman
2022	A	`conf`	GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion. INTERSPEECH Magdalena Proszewska, Grzegorz Beringer, Daniel Sáez-Trigueros, Thomas Merritt, Abdelhamid Ezzerg, Roberto Barra-Chicote
2022	J	`jnl`	GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion. CoRR Magdalena Proszewska, Grzegorz Beringer, Daniel Sáez-Trigueros, Thomas Merritt, Abdelhamid Ezzerg, Roberto Barra-Chicote
2022	—	`conf`	Remap, Warp and Attend: Non-Parallel Many-to-Many Accent Conversion with Normalizing Flows. SLT Abdelhamid Ezzerg, Thomas Merritt, Kayoko Yanagisawa, Piotr Bilinski, Magdalena Proszewska, Kamil Pokora, Renard Korzeniowski, Roberto Barra-Chicote, Daniel Korzekwa
2022	Misc	`conf`	Text-Free Non-Parallel Many-To-Many Voice Conversion Using Normalising Flow. ICASSP Thomas Merritt, Abdelhamid Ezzerg, Piotr Bilinski, Magdalena Proszewska, Kamil Pokora, Roberto Barra-Chicote, Daniel Korzekwa
2022	J	`jnl`	Text-free non-parallel many-to-many voice conversion using normalising flows. CoRR Thomas Merritt, Abdelhamid Ezzerg, Piotr Bilinski, Magdalena Proszewska, Kamil Pokora, Roberto Barra-Chicote, Daniel Korzekwa
2021	Misc	`conf`	Camp: A Two-Stage Approach to Modelling Prosody in Context. ICASSP Zack Hodari, Alexis Moinet, Sri Karlapati, Jaime Lorenzo-Trueba, Thomas Merritt, Arnaud Joly, Ammar Abbas, Penny Karanasou, Thomas Drugman
2021	Misc	`conf`	Low-Resource Expressive Text-To-Speech Using Data Augmentation. ICASSP Goeric Huybrechts, Thomas Merritt, Giulia Comini, Bartek Perz, Raahil Shah, Jaime Lorenzo-Trueba
2021	—	`conf`	Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech. SSW Raahil Shah, Kamil Pokora, Abdelhamid Ezzerg, Viacheslav Klimkov, Goeric Huybrechts, Bartosz Putrycz, Daniel Korzekwa, Thomas Merritt
2021	J	`jnl`	Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech. CoRR Raahil Shah, Kamil Pokora, Abdelhamid Ezzerg, Viacheslav Klimkov, Goeric Huybrechts, Bartosz Putrycz, Daniel Korzekwa, Thomas Merritt
2020	J	`jnl`	Low-resource expressive text-to-speech using data augmentation. CoRR Goeric Huybrechts, Thomas Merritt, Giulia Comini, Bartek Perz, Raahil Shah, Jaime Lorenzo-Trueba
2020	J	`jnl`	Parallel WaveNet conditioned on VAE latent vectors. CoRR Jonas Rohnke, Thomas Merritt, Jaime Lorenzo-Trueba, Adam Gabrys, Vatsal Aggarwal, Alexis Moinet, Roberto Barra-Chicote
2019	Misc	`conf`	Effect of Data Reduction on Sequence-to-sequence Neural TTS. ICASSP Javier Latorre, Jakub Lachowicz, Jaime Lorenzo-Trueba, Thomas Merritt, Thomas Drugman, Srikanth Ronanki, Viacheslav Klimkov
2019	J	`jnl`	In Other News: A Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited Data. CoRR Nishant Prateek, Mateusz Lajszczak, Roberto Barra-Chicote, Thomas Drugman, Jaime Lorenzo-Trueba, Thomas Merritt, Srikanth Ronanki, Trevor Wood
2019	—	`conf`	In Other News: a Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited Data. NAACL-HLT (2) Nishant Prateek, Mateusz Lajszczak, Roberto Barra-Chicote, Thomas Drugman, Jaime Lorenzo-Trueba, Thomas Merritt, Srikanth Ronanki, Trevor Wood
2019	A	`conf`	Towards Achieving Robust Universal Neural Vocoding. INTERSPEECH Jaime Lorenzo-Trueba, Thomas Drugman, Javier Latorre, Thomas Merritt, Bartosz Putrycz, Roberto Barra-Chicote, Alexis Moinet, Vatsal Aggarwal
2018	J	`jnl`	Analysing Shortcomings of Statistical Parametric Speech Synthesis. CoRR Gustav Eje Henter, Simon King, Thomas Merritt, Gilles Degottex
2018	—	`conf`	Comprehensive Evaluation of Statistical Speech Waveform Synthesis. SLT Thomas Merritt, Bartosz Putrycz, Adam Nadolski, Tianjun Ye, Daniel Korzekwa, Wiktor Dolecki, Thomas Drugman, Viacheslav Klimkov, Alexis Moinet, Andrew Breen, Rafal Kuklinski, Nikko Strom, Roberto Barra-Chicote
2018	J	`jnl`	Comprehensive evaluation of statistical speech waveform synthesis. CoRR Thomas Merritt, Bartosz Putrycz, Adam Nadolski, Tianjun Ye, Daniel Korzekwa, Wiktor Dolecki, Thomas Drugman, Viacheslav Klimkov, Alexis Moinet, Andrew Breen, Rafal Kuklinski, Nikko Strom, Roberto Barra-Chicote
2018	J	`jnl`	Effect of data reduction on sequence-to-sequence neural TTS. CoRR Javier Latorre, Jakub Lachowicz, Jaime Lorenzo-Trueba, Thomas Merritt, Thomas Drugman, Srikanth Ronanki, Klimkov Viacheslav
2018	J	`jnl`	Robust universal neural vocoding. CoRR Jaime Lorenzo-Trueba, Thomas Drugman, Javier Latorre, Thomas Merritt, Bartosz Putrycz, Roberto Barra-Chicote
2017	—	`—`	Overcoming the limitations of statistical parametric speech synthesis. Thomas Merritt
2017	A	`conf`	Phrase Break Prediction for Long-Form Reading TTS: Exploiting Text Structure Information. INTERSPEECH Viacheslav Klimkov, Adam Nadolski, Alexis Moinet, Bartosz Putrycz, Roberto Barra-Chicote, Thomas Merritt, Thomas Drugman
2016	Misc	`conf`	Deep neural network-guided unit selection synthesis. ICASSP Thomas Merritt, Robert A. J. Clark, Zhizheng Wu, Junichi Yamagishi, Simon King
2016	Misc	`conf`	From HMMS to DNNS: Where do the improvements come from? ICASSP Oliver Watts, Gustav Eje Henter, Thomas Merritt, Zhizheng Wu, Simon King
2016	—	`conf`	The CSTR entry to the Blizzard Challenge 2016. Blizzard Challenge Thomas Merritt, Srikanth Ronanki, Zhizheng Wu, Oliver Watts
2015	Misc	`conf`	Attributing modelling errors in HMM synthesis by stepping gradually from natural to modelled speech. ICASSP Thomas Merritt, Javier Latorre, Simon King
2015	A	`conf`	Deep neural network context embeddings for model selection in rich-context HMM synthesis. INTERSPEECH Thomas Merritt, Junichi Yamagishi, Zhizheng Wu, Oliver Watts, Simon King
2014	A	`conf`	A flexible front-end for HTS. INTERSPEECH Matthew P. Aylett, Rasmus Dall, Arnab Ghoshal, Gustav Eje Henter, Thomas Merritt
2014	A	`conf`	Investigating source and filter contributions, and their interaction, to statistical parametric speech synthesis. INTERSPEECH Thomas Merritt, Tuomo Raitio, Simon King
2014	A	`conf`	Measuring the perceptual effects of modelling assumptions in speech synthesis using stimuli constructed from repeated natural speech. INTERSPEECH Gustav Eje Henter, Thomas Merritt, Matt Shannon, Catherine Mayo, Simon King
2013	—	`conf`	Investigating the shortcomings of HMM synthesis. SSW Thomas Merritt, Simon King