Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

10

ACL
1997

favoriteEmaildiscussreport

141views Computational Linguistics» more ACL 1997»

A Structured Language Model

13 years 5 months ago

A Structured Language Model

Download research.microsoft.com

A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history — thus enabling the use of extended distance dependencies — in an attempt to complement the locality of currently used n-gram Markov models. The model, its probabilistic parametrization, a reestimation algorithm for the model parameters and a set of experiments meant to evaluate its potential for speech recognition are presented.

Ciprian Chelba

Real-time Traffic

ACL 1997 | ACL 2007 | Model Parameters | N-gram Markov Models | Speech Recognition |

claim paper

Related Content

» Uniform Support for Modeling Crosscutting Structure

» Recognition Performance of a Structured Language Model

» Learning Biases for the Evolution of Linguistic Structure An Associative Network Model

» Incremental Parsing Models for Dialog Task Structure

» Using Random Forests in the Structured Language Model

» Structural Model Architecture for Software Designers

» Structural Transitive and Latent Models for Biographic Fact Extraction

» Unsupervised Learning of Dependency Structure for Language Modeling

» Computational Structure of Generative Phonology and its Relation to Language Comprehension

» An Alignment Algorithm Using Belief Propagation and a StructureBased Distortion Model

Post Info
More Details (n/a)

Added	01 Nov 2010
Updated	01 Nov 2010
Type	Conference
Year	1997
Where	ACL
Authors	Ciprian Chelba

Comments (0)