V
Vincent Vanhoucke
Researcher at Google
Publications - 84
Citations - 118049
Vincent Vanhoucke is an academic researcher from Google. The author has contributed to research in topics: Artificial neural network & Reinforcement learning. The author has an hindex of 42, co-authored 75 publications receiving 87969 citations. Previous affiliations of Vincent Vanhoucke include Stanford University.
Papers
More filters
Posted Content
Policies Modulating Trajectory Generators
Atil Iscen,Ken Caluwaerts,Jie Tan,Tingnan Zhang,Erwin Coumans,Vikas Sindhwani,Vincent Vanhoucke +6 more
TL;DR: In this paper, the authors propose an architecture for learning complex controllable behaviors by having simple Policies Modulate Trajectory Generators (PMTG), a powerful combination that can provide both memory and prior knowledge to the controller.
Proceedings ArticleDOI
Confidence scoring and rejection using multi-pass speech recognition.
TL;DR: A set of criteria is proposed, which determine at run time when rescoring using a second pass is expected to improve the rejection performance of an automatic speech recognition system.
Proceedings ArticleDOI
Mixtures of inverse covariances
Vincent Vanhoucke,Ananth Sankar +1 more
TL;DR: A model which approximates full covariances in a Gaussian mixture while reducing significantly both the number of parameters to estimate and the computations required to evaluate the Gaussian likelihoods is described.
Journal ArticleDOI
Mixtures of inverse covariances
Vincent Vanhoucke,Ananth Sankar +1 more
TL;DR: A model which approximates full covariances in a Gaussian mixture while reducing significantly both the number of parameters to estimate and the computations required to evaluate the Gaussian likelihoods is described.
Patent
Frame-level combination of deep neural network and gaussian mixture models
TL;DR: In this paper, a method and system for frame-level merging of HMM state predictions determined by different techniques is disclosed, where audio input signals are transformed into a first and second sequence of feature vector, the sequences corresponding to each other and to a temporal sequence of frames of the audio input signal on a frame-by-frame basis.