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
Proceedings ArticleDOI
Reducing the Computational Complexity of Multimicrophone Acoustic Models with Integrated Feature Extraction.
Tara N. Sainath,Arun Narayanan,Ron Weiss,Ehsan Variani,Kevin W. Wilson,Michiel Bacchiani,Izhak Shafran +6 more
TL;DR: Several different approaches to reduce the complexity of this multichannel neural network model by reducing the stride of the convolution operation and by implementing filters in the frequency domain are presented.
Proceedings ArticleDOI
Wave-Tacotron: Spectrogram-Free End-to-End Text-to-Speech Synthesis
TL;DR: The authors proposed a sequence-to-sequence neural network which directly generates speech waveforms from text inputs by incorporating a normalizing flow into the autoregressive decoder loop, which can be optimized directly with maximum likelihood, with-out using intermediate, hand-designed features.
Proceedings ArticleDOI
Grid-based temporal logic inference
Prashant Vaidyanathan,Rachael Ivison,Giuseppe Bombara,Nicholas A. DeLateur,Ron Weiss,Douglas Densmore,Calin Belta +6 more
TL;DR: A new algorithm to infer temporal logic properties of a system from data consisting of a set of finite time system traces by discretizing the entire domain and codomain of the system traces is introduced.
Proceedings ArticleDOI
A Dynamical Biomolecular Neural Network
TL;DR: A Biomolecular Neural Network (BNN), a dynamical chemical reaction network which faithfully implements ANN computations and which is unconditionally stable with respect to its parameters when composed into deeper networks is proposed.
Posted Content
Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separation
TL;DR: It is demonstrated that this model can be trained to normalize speech from any speaker regardless of accent, prosody, and background noise, into the voice of a single canonical target speaker with a fixed accent and consistent articulation and prosody.