Cassia Valentini-Botinhao
Cassia Valentini-Botinhao
Verified email at sms.ed.ac.uk
Title
Cited by
Cited by
Year
Deep Neural Networks employing multi-task learning and stacked bottleneck features for speech synthesis
Z Wu, C Valentini-Botinhao, O Watts, S King
ICASSP, 2015
2762015
Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech.
C Valentini-Botinhao, X Wang, S Takaki, J Yamagishi
SSW, 146-152, 2016
1192016
Evaluating the intelligibility benefit of speech modifications in known noise conditions
M Cooke, C Mayo, C Valentini-Botinhao, Y Stylianou, B Sauert, Y Tang
Speech Communication 55 (4), 572-585, 2013
1162013
Intelligibility-enhancing speech modifications: the Hurricane Challenge
M Cooke, C Mayo, C Valentini-Botinhao
Interspeech, Lyon, France, 2013
1032013
A deep generative architecture for postfiltering in statistical parametric speech synthesis
LH Chen, T Raitio, C Valentini-Botinhao, ZH Ling, J Yamagishi
IEEE/ACM Transactions on Audio, Speech, and Language Processing 23 (11 …, 2015
532015
Noisy speech database for training speech enhancement algorithms and tts models
C Valentini-Botinhao
University of Edinburgh. School of Informatics. Centre for Speech Technology …, 2017
452017
Can objective measures predict the intelligibility of modified HMM-based synthetic speech in noise?
C Valentini-Botinhao, J Yamagishi, S King
Interspeech, 2011
442011
Speech enhancement for a noise-robust text-to-speech synthesis system using deep recurrent neural networks
CV Botinhao, X Wang, S Takaki, J Yamagishi
Interspeech 2016, 352-356, 2016
432016
DNN-Based Stochastic Postfilter for HMM-Based Speech Synthesis
LH Chen, T Raitio, C Valentini-Botinhao, J Yamagishi, ZH Ling
Fifteenth Annual Conference of the International Speech Communication …, 2014
422014
Are we using enough listeners? No!—an empirically-supported critique of Interspeech 2014 TTS evaluations
M Wester, C Valentini-Botinhao, GE Henter
Sixteenth Annual Conference of the International Speech Communication …, 2015
362015
Modelling acoustic feature dependencies with artificial neural networks: Trajectory-RNADE
B Uria, I Murray, S Renals, C Valentini-Botinhao, J Bridle
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
342015
Intelligibility enhancement of HMM-generated speech in additive noise by modifying Mel cepstral coefficients to increase the glimpse proportion
C Valentini-Botinhao, J Yamagishi, S King, R Maia
Computer Speech & Language 28 (2), 665-686, 2014
302014
Mel cepstral coefficient modification based on the Glimpse Proportion measure for improving the intelligibility of HMM-generated synthetic speech in noise
C Valentini-Botinhao, J Yamagishi, S King
Interspeech, 2012
292012
Direct Modelling of Magnitude and Phase Spectra for Statistical Parametric Speech Synthesis.
F Espic, C Valentini-Botinhao, S King
INTERSPEECH, 1383-1387, 2017
262017
Evaluation of objective measures for intelligibility prediction of HMM-based synthetic speech in noise
C Valentini-Botinhao, J Yamagishi, S King
ICASSP, 5112-5115, 2011
262011
Evaluating the predictions of objective intelligibility metrics for modified and synthetic speech
Y Tang, M Cooke, C Valentini-Botinhao
Computer Speech & Language 35, 73-92, 2016
232016
Cepstral analysis based on the Glimpse proportion measure for improving the intelligibility of HMM-based synthetic speech in noise
C Valentini-Botinhao, R Maia, J Yamagishi, S King, H Zen
ICASSP, 3997-4000, 2012
222012
Towards minimum perceptual error training for DNN-based speech synthesis
C Valentini-Botinhao, Z Wu, S King
Sixteenth annual conference of the international speech communication …, 2015
212015
Speech enhancement of noisy and reverberant speech for text-to-speech
C Valentini-Botinhao, J Yamagishi
IEEE/ACM Transactions on Audio, Speech, and Language Processing 26 (8), 1420 …, 2018
142018
Where do the improvements come from in sequence-to-sequence neural TTS?
O Watts, GE Henter, J Fong, C Valentini-Botinhao
2019 ISCA Speech Synthesis Workshop (SSW) 10, 217-222, 2019
122019
The system can't perform the operation now. Try again later.
Articles 1–20