Thomas Merritt

发表

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

Zhizheng Wu, Oliver Watts, Simon King, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

Oliver Watts, Simon King, Junichi Yamagishi, 2015, Interspeech.

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

Simon King, Thomas Merritt, Javier Latorre, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

Srikanth Ronanki, Thomas Drugman, Thomas Merritt, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

INTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association

Matthew P. Aylett, Gustav Eje Henter, Rasmus Dall, 2014 .

Low-resource expressive text-to-speech using data augmentation

Thomas Merritt, Jaime Lorenzo-Trueba, Goeric Huybrechts, 2020 .

Rapid, cost-effective and scalable gmp-compliant simian adenovirus-vectored vaccine production for early-phase clinical trials using entirely disposable product-contact components

Thomas Merritt, Alexander D. Douglas, Sofiya Fedosyuk, 2018 .

Listening test materials for "From HMMs to DNNs: Where do the improvements come from?"

Oliver Watts, Simon King, Gustav Eje Henter, 2016 .

Overcoming the limitations of statistical parametric speech synthesis

Thomas Merritt, Thomas Merritt, 2017 .

Listening test materials for "Deep neural network-guided unit selection synthesis"

Simon King, Junichi Yamagishi, Zhizheng Wu, 2016 .

Comprehensive Evaluation of Statistical Speech Waveform Synthesis

Adam Nadolski, Nikko Strom, Thomas Drugman, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

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

Adam Nadolski, Thomas Drugman, Thomas Merritt, 2017, INTERSPEECH.

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

Zhizheng Wu, Oliver Watts, Simon King, 2015, INTERSPEECH.

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

Simon King, Tuomo Raitio, Thomas Merritt, 2014, INTERSPEECH.

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

Simon King, Gustav Eje Henter, Matt Shannon, 2014, INTERSPEECH.

Robust universal neural vocoding pdf

Thomas Drugman, Thomas Merritt, Jaime Lorenzo-Trueba, 2018, ArXiv.

Deep neural network-guided unit selection synthesis

Zhizheng Wu, Simon King, Junichi Yamagishi, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

Srikanth Ronanki, Thomas Merritt, Jaime Lorenzo-Trueba, 2019, NAACL.

A flexible front-end for HTS

Matthew P. Aylett, Gustav Eje Henter, Rasmus Dall, 2014, INTERSPEECH.

Towards Achieving Robust Universal Neural Vocoding

Thomas Drugman, Thomas Merritt, Alexis Moinet, 2018, INTERSPEECH.

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

Thomas Merritt, Zack Hodari, Alexis Moinet, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Genetic structure and phenotypic plasticity of yellow perch (Perca flavescens) populations influenced by habitat, predation, and contamination gradients.

Thomas Merritt, Ashley Tremblay, David Lesbarreres, 2008, Integrated environmental assessment and management.

Analysing Shortcomings of Statistical Parametric Speech Synthesis pdf

Simon King, Gustav Eje Henter, Gilles Degottex, 2018, ArXiv.

The CSTR entry to the Blizzard Challenge 2016

Srikanth Ronanki, Oliver Watts, Thomas Merritt, 2016 .

Investigating the shortcomings of HMM synthesis

Simon King, Thomas Merritt, Thomas Merritt, 2013, SSW.

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

Daniel Korzekwa, Thomas Merritt, Goeric Huybrechts, 2021, SSW.

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

Thomas Drugman, Thomas Merritt, Zack Hodari, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Repeated Harvard Sentence Prompts corpus version 0.5

Simon King, Gustav Eje Henter, Matt Shannon, 2014 .