METHOD AND APPARATUS FOR TRAINING LANGUAGE MODEL, AND METHOD AND APPARATUS FOR RECOGNIZING LANGUAGE

A method and apparatus for training a language model, include generating a first training feature vector sequence and a second training feature vector sequence from training data. The method is configured to perform forward estimation of a neural network based on the first training feature vector se...

Full description

Saved in:
Bibliographic Details
Main Authors CHOI HEEYOUL, YOO SANG HYUN, MIN YUNHONG, LEE HOSHIK, LEE YEHA, LEE JIHYUN, LEE HODONG, CHOI YOUNGSANG
Format Patent
LanguageEnglish
Published 21.07.2016
Subjects
ACOUSTICS
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
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:A method and apparatus for training a language model, include generating a first training feature vector sequence and a second training feature vector sequence from training data. The method is configured to perform forward estimation of a neural network based on the first training feature vector sequence, and perform backward estimation of the neural network based on the second training feature vector sequence. The method is further configured to train a language model based on a result of the forward estimation and a result of the backward estimation.
Bibliography:Application Number: US201614992129