P
Patrick Haffner
Researcher at AT&T Labs
Publications - 97
Citations - 57875
Patrick Haffner is an academic researcher from AT&T Labs. The author has contributed to research in topics: Support vector machine & Speaker recognition. The author has an hindex of 32, co-authored 97 publications receiving 42604 citations. Previous affiliations of Patrick Haffner include Nuance Communications & Carnegie Mellon University.
Papers
More filters
Patent
System and method for rapid customization of speech recognition models
TL;DR: In this paper, the authors present a method for generating domain-specific speech recognition models for a domain of interest by combining and tuning existing speech recognition model when a speech recognizer does not have access to a speech recognition system for that domain of the interest and when available domain specific data is below a minimum desired threshold.
Patent
System and method for automatic generation of a natural language understanding model
Lee Begeja,Mazin G. Rahim,Allen Louis Gorin,Behzad Shahraray,David Crawford Gibbon,Zhu Liu,Bernard S. Renger,Patrick Haffner,Harris Drucker,Steven H. Lewis +9 more
TL;DR: In this paper, a user experience person labels the transcribed data (e.g., 3000 utterances) using a set of interactive tools, and the labeled data is then stored in a processed data database.
Proceedings ArticleDOI
Browsing through high quality document images with DjVu
TL;DR: Presents a new image compression technique called DjVu that is specifically geared towards the compression of high-resolution, high-quality images of scanned documents in color, and is available as a plug-in for popular Web browsers.
Proceedings Article
Fast back-propagation learning methods for large phonemic neural networks.
TL;DR: Several improvements in the Back-Propagation procedure are proposed to increase training speed, and their limitations with respect to generalization are discussed.
Patent
Application signature based traffic classification
TL;DR: In this article, a method for identifying traffic to an application including the steps of monitoring communication traffic in a network, identifying data from communication traffic content, and constructing a model for mapping the communication traffic for an application derived from data identified from the traffic content is described.