Thomas Merritt
Thomas Merritt
Amazon
Verified email at amazon.co.uk
TitleCited byYear
From HMMs to DNNs: where do the improvements come from?
O Watts, GE Henter, T Merritt, Z Wu, S King
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
572016
Deep neural network-guided unit selection synthesis
T Merritt, RAJ Clark, Z Wu, J Yamagishi, S King
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
482016
Measuring the perceptual effects of modelling assumptions in speech synthesis using stimuli constructed from repeated natural speech
GE Henter, T Merritt, M Shannon, C Mayo, S King
Fifteenth Annual Conference of the International Speech Communication …, 2014
392014
Attributing modelling errors in HMM synthesis by stepping gradually from natural to modelled speech
T Merritt, J Latorre, S King
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
222015
Investigating source and filter contributions, and their interaction, to statistical parametric speech synthesis
T Merritt, T Raitio, S King
Fifteenth Annual Conference of the International Speech Communication …, 2014
182014
Deep neural network context embeddings for model selection in rich-context HMM synthesis
T Merritt, J Yamagishi, Z Wu, O Watts, S King
Sixteenth Annual Conference of the International Speech Communication …, 2015
132015
Investigating the shortcomings of HMM synthesis
T Merritt, S King
Eighth ISCA Workshop on Speech Synthesis, 2013
132013
Effect of data reduction on sequence-to-sequence neural tts
J Latorre, J Lachowicz, J Lorenzo-Trueba, T Merritt, T Drugman, ...
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
122019
Robust universal neural vocoding
J Lorenzo-Trueba, T Drugman, J Latorre, T Merritt, B Putrycz, ...
arXiv preprint arXiv:1811.06292, 2018
102018
Expressive speech synthesis for storytelling: the INNOETICS’entry to the blizzard challenge 2016
S Raptis, P Tsiakoulis, A Chalamandaris, S Karabetsos
Proc. Blizzard Challenge, 2016
102016
A flexible front-end for HTS
MP Aylett, R Dall, A Ghoshal, GE Henter, T Merritt
Fifteenth Annual Conference of the International Speech Communication …, 2014
92014
Comprehensive evaluation of statistical speech waveform synthesis
T Merritt, B Putrycz, A Nadolski, T Ye, D Korzekwa, W Dolecki, T Drugman, ...
2018 IEEE Spoken Language Technology Workshop (SLT), 325-331, 2018
62018
Phrase Break Prediction for Long-Form Reading TTS: Exploiting Text Structure Information.
V Klimkov, A Nadolski, A Moinet, B Putrycz, R Barra-Chicote, T Merritt, ...
Interspeech, 1064-1068, 2017
52017
Listening test materials for
T Merritt, J Yamagishi, Z Wu, O Watts, S King
Deep neural network context embeddings for model selection in rich-context …, 2015
52015
In other news: A bi-style text-to-speech model for synthesizing newscaster voice with limited data
N Prateek, M Łajszczak, R Barra-Chicote, T Drugman, J Lorenzo-Trueba, ...
arXiv preprint arXiv:1904.02790, 2019
42019
Towards achieving robust universal neural vocoding
J Lorenzo-Trueba, T Drugman, J Latorre, T Merritt, B Putrycz, ...
arXiv preprint arXiv:1811.06292, 2018
42018
Overcoming the limitations of statistical parametric speech synthesis
T Merritt
The University of Edinburgh, 2017
12017
Contextual text-to-speech processing
RB Chicote, J Latorre, AF Nadolski, V Klimkov, TE Merritt
US Patent 10,475,438, 2019
2019
Analysing Shortcomings of Statistical Parametric Speech Synthesis
GE Henter, S King, T Merritt, G Degottex
arXiv preprint arXiv:1807.10941, 2018
2018
Analysing Shortcomings of Statistical Parametric Speech Synthesis
G Eje Henter, S King, T Merritt, G Degottex
arXiv preprint arXiv:1807.10941, 2018
2018
The system can't perform the operation now. Try again later.
Articles 1–20