Statistical language model adaptation: review and perspectives
JR Bellegarda - Speech communication, 2004 - Elsevier
Speech recognition performance is severely affected when the lexical, syntactic, or semantic
characteristics of the discourse in the training and recognition tasks differ. The aim of …
characteristics of the discourse in the training and recognition tasks differ. The aim of …
Applications of topic models
How can a single person understand what's going on in a collection of millions of
documents? This is an increasingly common problem: sifting through an organization's e …
documents? This is an increasingly common problem: sifting through an organization's e …
[图书][B] Markov models for pattern recognition: from theory to applications
GA Fink - 2014 - books.google.com
Markov models are extremely useful as a general, widely applicable tool for many areas in
statistical pattern recognition. This unique text/reference places the formalism of Markov …
statistical pattern recognition. This unique text/reference places the formalism of Markov …
Modelling out-of-vocabulary words for robust speech recognition
I Bazzi - 2002 - dspace.mit.edu
This thesis concerns the problem of unknown or out-of-vocabulary (OOV) words in
continuous speech recognition. Most of today's state-of-the-art speech recognition systems …
continuous speech recognition. Most of today's state-of-the-art speech recognition systems …
Spoken language understanding: A survey
R De Mori - 2007 IEEE Workshop on Automatic Speech …, 2007 - ieeexplore.ieee.org
A survey of research on spoken language understanding is presented. It covers aspects of
knowledge representation, automatic interpretation strategies, semantic grammars …
knowledge representation, automatic interpretation strategies, semantic grammars …
Efficient lattice rescoring using recurrent neural network language models
Recurrent neural network language models (RNNLM) have become an increasingly popular
choice for state-of-the-art speech recognition systems due to their inherently strong …
choice for state-of-the-art speech recognition systems due to their inherently strong …
Language model adaptation
R DeMori, M Federico - Computational models of speech pattern …, 1999 - Springer
This paper reviews methods for language model adaptation. Paradigms and basic methods
are first introduced. Basic theory is presented for maximum a-posteriori estimation, mixture …
are first introduced. Basic theory is presented for maximum a-posteriori estimation, mixture …
[PDF][PDF] Language model adaptation using dynamic marginals.
A new method is presented to quickly adapt a given language model to local text
characteristics. The basic approach is to choose the adaptive models as close as possible to …
characteristics. The basic approach is to choose the adaptive models as close as possible to …
Apparatus, method, and medium for generating grammar network for use in speech recognition and dialogue speech recognition
K Hwang - US Patent 7,606,708, 2009 - Google Patents
A method, apparatus, and medium for generating a grammar network for speech recognition
and a dialogue speech recognition are provided. A method, apparatus, and medium for …
and a dialogue speech recognition are provided. A method, apparatus, and medium for …
PPM-Decay: A computational model of auditory prediction with memory decay
PMC Harrison, R Bianco, M Chait… - PLoS computational …, 2020 - journals.plos.org
Statistical learning and probabilistic prediction are fundamental processes in auditory
cognition. A prominent computational model of these processes is Prediction by Partial …
cognition. A prominent computational model of these processes is Prediction by Partial …