R
Ron Weiss
Researcher at Massachusetts Institute of Technology
Publications - 301
Citations - 110805
Ron Weiss is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Synthetic biology & Speech synthesis. The author has an hindex of 82, co-authored 292 publications receiving 89189 citations. Previous affiliations of Ron Weiss include French Institute for Research in Computer Science and Automation & Google.
Papers
More filters
Journal ArticleDOI
In Vivo Validation of a Reversible Small Molecule-Based Switch for Synthetic Self-Amplifying mRNA Regulation.
Séan Mc Cafferty,Joyca De Temmerman,Tasuku Kitada,Jacob R. Becraft,Ron Weiss,Darrell J. Irvine,Mathias Devreese,Siegrid De Baere,Francis Combes,Niek N. Sanders +9 more
TL;DR: The in vivo utility of a synthetic self-amplifying mRNA (RNA replicon) whose expression can be turned off using a genetic switch that responds to oral administration of trimethoprim (TMP), an FDA-approved small-molecule drug is validated.
Proceedings ArticleDOI
WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
TL;DR: This article proposed WaveGrad 2, a non-autoregressive generative model for text-to-speech synthesis, which is trained to estimate the gradient of the log conditional density of the waveform given a phoneme sequence.
Journal ArticleDOI
Principles for the design of multicellular engineered living systems
Onur Aydın,Austin P. Passaro,Rituraj Raman,Samantha E. Spellicy,Robert P Weinberg,Roger D. Kamm,Matthew Sample,George A. Truskey,Jeremiah J. Zartman,Roy D. Dar,Sebastian Palacios,Jason Wang,Jesse Tordoff,Nuria Montserrat,Rashid Bashir,M. Taher A. Saif,Ron Weiss +16 more
TL;DR: Design principles and a blueprint for forward production of robust and standardized M-CELS are introduced, which may undergo variable reiterations through the classic design-build-test-debug cycle.
Posted Content
Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior
Guangzhi Sun,Yu Zhang,Ron Weiss,Yuan Cao,Heiga Zen,Andrew Rosenberg,Bhuvana Ramabhadran,Yonghui Wu +7 more
TL;DR: This paper proposed a sequential prior in a discrete latent space which can generate more naturally sounding samples, which is accomplished by discretizing the latent features using vector quantization (VQ), and separately training an autoregressive (AR) prior model over the result.
Patent
End-to-end text-to-speech conversion
Samuel Bengio,Yuxuan Wang,Zongheng Yang,Zhifeng Chen,Yonghui Wu,Ioannis Agiomyrgiannakis,Ron Weiss,Navdeep Jaitly,Ryan Rifkin,Robert A. J. Clark,Quoc V. Le,Russell J. Ryan,Ying Xiao +12 more
TL;DR: In this article, a sequence-to-sequence recurrent neural network (S2RNN) is used to generate a spectrogram of a verbal utterance of a sequence of characters in a particular natural language.