J
Javier Latorre
Researcher at Amazon.com
Publications - 49
Citations - 1022
Javier Latorre is an academic researcher from Amazon.com. The author has contributed to research in topics: Speech synthesis & Hidden Markov model. The author has an hindex of 19, co-authored 48 publications receiving 931 citations. Previous affiliations of Javier Latorre include Toshiba & Tokyo Institute of Technology.
Papers
More filters
Journal ArticleDOI
Statistical Parametric Speech Synthesis Based on Speaker and Language Factorization
Heiga Zen,Norbert Braunschweiler,Sabine Buchholz,Mark J. F. Gales,Kate Knill,Sacha Krstulovic,Javier Latorre +6 more
TL;DR: Experimental results on statistical parametric speech synthesis show that the proposed framework enables data from multiple speakers in different languages to be used to: train a synthesis system; synthesize speech in a language using speaker characteristics estimated in a different language; and adapt to a new language.
Proceedings Article
Crowdsourcing Preference Tests, and How to Detect Cheating.
Sabine Buchholz,Javier Latorre +1 more
TL;DR: An approach to crowdsource the evaluation of TTS systems by preference tests and it is shown that at least one type of cheating becomes more prevalent over time if left unchecked and metrics to exclude cheaters are developed.
Proceedings ArticleDOI
Towards achieving robust universal neural vocoding
Jaime Lorenzo-Trueba,Thomas Drugman,Javier Latorre,Thomas Merritt,Bartosz Putrycz,Roberto Barra-Chicote,Alexis Moinet,Vatsal Aggarwal +7 more
TL;DR: A WaveRNN-based vocoder is shown to be capable of generating speech of consistently good quality regardless of whether the input spectrogram comes from a speaker or style seen during training or from an out-of-domain scenario when the recording conditions are studio-quality.
Journal ArticleDOI
New approach to the polyglot speech generation by means of an HMM-based speaker adaptable synthesizer
TL;DR: The performance obtained with the HMM-based polyglot synthesis method is better than that of methods based on phone mapping for both adaptation and synthesis, and can be used to create synthesizers for languages where no speech resources are available.
Proceedings ArticleDOI
Multilevel parametric-base F0 model for speech synthesis
Javier Latorre,Masami Akamine +1 more
TL;DR: A sub-jective test showed a clear preference for the proposed model against the previous HMM-based baseline, and a new F0 model for speech synthesis based on the parameterization of the logF0 contour of the syllables.