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
Patent
Adaptive auto-encoders
TL;DR: In this article, an adaptive auto-encoder is proposed to compensate for supra-phonetic features by reducing the magnitude of an error signal corresponding to a difference between the normalized signal and the recovered form of the quantitative measures.
Proceedings ArticleDOI
Automatic training set segmentation for multi-pass speech recognition
TL;DR: This work describes an extensible automatic solution to automatic speech recognition that requires no manual gender or channel labeling and clusters the training data into datasets containing utterances whose acoustics are very similar across the entire utterance.
Proceedings ArticleDOI
Unsupervised Discovery and Training of Maximally Dissimilar Cluster Models
TL;DR: A technique which allows us to perform acoustic modeling at scale on large amounts of data by learning a treestructured partition of the acoustic space is described and it is demonstrated that it can significantly improve recognition accuracy in various conditions through unsupervised Maximum Mutual Information (MMI) training.
Proceedings ArticleDOI
X-Ray: Mechanical Search for an Occluded Object by Minimizing Support of Learned Occupancy Distributions
TL;DR: X-Ray, an algorithm based on learned occupancy distributions that minimizes support of the learned distribution as part of a mechanical search policy in both simulated and real environments, is introduced.