Gerald Penn

University of Toronto
0000-0003-3553-8305
http://www.cs.toronto.edu/~gpenn
Publications177
h-index30
Citations5,341
Highly Influential Citations307
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • Cosmin Munteanu
  • 147 Publications • 1,693 Citations
  • Geoffrey E. Hinton
  • 404 Publications • 352,195 Citations
  • L. Deng
  • 532 Publications • 49,031 Citations
  • Abdel-rahman Mohamed
  • 108 Publications • 28,932 Citations
  • Publications
  • Influence
Convolutional Neural Networks for Speech Recognition
TLDR
It is shown that further error rate reduction can be obtained by using convolutional neural networks (CNNs), and a limited-weight-sharing scheme is proposed that can better model speech features.
View on ACM
Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition
TLDR
The proposed CNN architecture is applied to speech recognition within the framework of hybrid NN-HMM model to use local filtering and max-pooling in frequency domain to normalize speaker variance to achieve higher multi-speaker speech recognition performance.
View on IEEE
Bubble Sets: Revealing Set Relations with Isocontours over Existing Visualizations
TLDR
B Bubble Sets is introduced as a visualization technique for data that has both a primary data relation with a semantically significant spatial organization and a significant set membership relation in which members of the same set are not necessarily adjacent in the primary layout.
View on IEEE
ALE : the attribute logic engine user's guide, version 2.0.1
ale 3.0 is completely compatible with ale 2.0 grammars, and adds the following new features: • A semantic-head-driven generator, based on the algorithm presented in Shieber et al. (1990). The…
Categorial grammars determined from linguistic data by unification
TLDR
The algorithm presented here extends an earlier one restricted to rigid categorial grammars, introduced in [4] and [5], by admitting non-rigid outputs, and introduces the notion of an optimal unifier, a natural generalization of that of a most general unifier.
View on Springer
Understanding how Deep Belief Networks perform acoustic modelling
TLDR
This paper illustrates how each of these three aspects contributes to the DBN's good recognition performance using both phone recognition performance on the TIMIT corpus and a dimensionally reduced visualization of the relationships between the feature vectors learned by the Dbns that preserves the similarity structure of the feature vector at multiple scales.
View on IEEE
DocuBurst: Visualizing Document Content using Language Structure
TLDR
DocuBurst is a radial, space‐filling layout of hyponymy (the IS‐A relation), overlaid with occurrence counts of words in a document of interest to provide visual summaries at varying levels of granularity.
View on Wiley
Deep bi-directional recurrent networks over spectral windows
TLDR
This paper applies a windowed (truncated) LSTM to conversational speech transcription, and finds that a limited context is adequate, and that it is not necessaary to scan the entire utterance.
View on IEEE
A Web-based Instructional Platform for Contraint-Based Grammar Formalisms and Parsing
TLDR
A web-based training framework comprising a set of topics that revolve around the use of feature structures as the core data structure in linguistic theory, its formal foundations, and its use in syntactic processing is proposed.
View on ACL
Accurate Context-Free Parsing with Combinatory Categorial Grammar
TLDR
It is proved that a wide range of CCGs are strongly context-free, including the CCG of CCG-bank and of the parser of Clark and Curran (2007), and it is train the PCFG parser of Petrov and Klein (2007) on CCGbank and achieve state of the art results in supertagging accuracy, PARSEVAL measures and dependency accuracy.
View on ACL
...
...