R
Roberto Barra-Chicote
Researcher at Amazon.com
Publications - 66
Citations - 984
Roberto Barra-Chicote is an academic researcher from Amazon.com. The author has contributed to research in topics: Speech synthesis & Computer science. The author has an hindex of 17, co-authored 58 publications receiving 707 citations. Previous affiliations of Roberto Barra-Chicote include Technical University of Madrid.
Papers
More filters
Proceedings Article
Towards Speaking Style Transplantation in Speech Synthesis
Jaime Lorenzo-Trueba,Roberto Barra-Chicote,Junichi Yamagishi,Oliver Watts,Juan Manuel Montero +4 more
TL;DR: This paper proposes a set of different techniques that could be used for extrapolating the expressiveness of proven high quality speaking style models into neutral speakers in HMM-based synthesis and proves that the deviations between neutral and speaking style average models can be learned and used to imbue expressiveness into target neutral speakers as intended.
Posted Content
From Speech-to-Speech Translation to Automatic Dubbing
Marcello Federico,Robert Enyedi,Roberto Barra-Chicote,Ritwik Giri,Umut Isik,Arvindh Krishnaswamy,Hassan Sawaf +6 more
TL;DR: A first subjective evaluation of automatic Dubbing of excerpts of TED Talks from English into Italian is reported, which measures the perceived naturalness of automatic dubbing and the relative importance of each proposed enhancement.
Proceedings ArticleDOI
Phrase Break Prediction for Long-form Reading TTS: Exploiting Text Structure Information
Viacheslav Klimkov,Adam Nadolski,Alexis Moinet,Bartosz Putrycz,Roberto Barra-Chicote,Thomas Merritt,Thomas Drugman +6 more
TL;DR: This paper presents how it has built phrasing models based on data extracted from audiobooks, and investigates how various types of textual features can improve phrase break prediction: part-of-speech (POS), guess POS (GPOS), dependency tree features and word embeddings.
Proceedings ArticleDOI
Evaluating and optimizing prosodic alignment for automatic dubbing
TL;DR: This paper focuses on recent progress on the prosodic alignment component, which aims at synchronizing the translated transcript with the original utterances, and presents empirical results for English-to-Italian dubbing on a publicly available collection of TED Talks.
Proceedings ArticleDOI
Interpretable Deep Learning Model for the Detection and Reconstruction of Dysarthric Speech
TL;DR: This paper proposed a multi-task supervised approach for predicting both the probability of dysarthric speech and the mel-spectrogram, which helps improve the detection and reconstruction of speech with higher accuracy, thanks to a low-dimensional latent space of the auto-encoder.