Classification filter for processing data for creating a language model

The method and apparatus utilize a filter to remove a variety of non-dictated words from data based on probability and improve the effectiveness of creating a language model.

Saved in:
Bibliographic Details
Main Authors ACERO ALEJANDRO, ODELL JULIAN J, MAHAJAN MILIND V, MAU PETER K. L, YU DONG
Format Patent
LanguageEnglish
Published 24.04.2012
Subjects
ACOUSTICS
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
Online AccessGet full text

Cover

More Information
Summary:The method and apparatus utilize a filter to remove a variety of non-dictated words from data based on probability and improve the effectiveness of creating a language model.
Bibliography:Application Number: US20050054819