scholarly journals A Batch Noise Contrastive Estimation Approach for Training Large Vocabulary Language Models

2017 ◽  
Author(s):  
Youssef Oualil ◽  
Dietrich Klakow
Keyword(s):  
Language Models ◽  
Large Vocabulary ◽  
Batch Noise

scholarly journals Strategies for Training Large Vocabulary Neural Language Models

2016 ◽  
Author(s):  
Wenlin Chen ◽  
David Grangier ◽  
Michael Auli
Keyword(s):  
Language Models ◽  
Large Vocabulary

POS-based language models for large vocabulary speech recognition on embedded systems

2005 ◽  
Author(s):  
Petra Witschel ◽  
Sergey Astrov ◽  
Gabriele Bakenecker ◽  
Josef G. Bauer ◽  
Harald Höge
Keyword(s):  
Speech Recognition ◽  
Embedded Systems ◽  
Language Models ◽  
Large Vocabulary ◽  
Large Vocabulary Speech Recognition

Large vocabulary SOUL neural network language models

2011 ◽  
Author(s):  
Hai-Son Le ◽  
Ilya Oparin ◽  
Abdel Messaoudi ◽  
Alexandre Allauzen ◽  
Jean-Luc Gauvain ◽  
...  
Keyword(s):  
Neural Network ◽  
Language Models ◽  
Large Vocabulary ◽  
Network Language

scholarly journals Using Morphological Data in Language Modeling for Serbian Large Vocabulary Speech Recognition

2019 ◽  
Vol 2019 ◽  
pp. 1-8 ◽  
Author(s):  
Edvin Pakoci ◽  
Branislav Popović ◽  
Darko Pekar
Keyword(s):  
Speech Recognition ◽  
Language Model ◽  
Recognition System ◽  
Language Modeling ◽  
Error Rates ◽  
Language Models ◽  
Morphological Data ◽  
Semantic Features ◽  
Automatic Speech Recognition System ◽  
Large Vocabulary

Serbian is in a group of highly inflective and morphologically rich languages that use a lot of different word suffixes to express different grammatical, syntactic, or semantic features. This kind of behaviour usually produces a lot of recognition errors, especially in large vocabulary systems—even when, due to good acoustical matching, the correct lemma is predicted by the automatic speech recognition system, often a wrong word ending occurs, which is nevertheless counted as an error. This effect is larger for contexts not present in the language model training corpus. In this manuscript, an approach which takes into account different morphological categories of words for language modeling is examined, and the benefits in terms of word error rates and perplexities are presented. These categories include word type, word case, grammatical number, and gender, and they were all assigned to words in the system vocabulary, where applicable. These additional word features helped to produce significant improvements in relation to the baseline system, both for n-gram-based and neural network-based language models. The proposed system can help overcome a lot of tedious errors in a large vocabulary system, for example, for dictation, both for Serbian and for other languages with similar characteristics.

Sign in / Sign up

Export Citation Format

Share Document