Matches in SemOpenAlex for { <https://semopenalex.org/work/W2770176249> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2770176249 abstract "Abstract : Recurrent neural network language models (RNNLMs) have become an increasingly popular choice for speech and language processing tasks including automatic speech recognition (ASR). As the generalization patterns of RNNLMs and n-gram LMs are inherently different, RNNLMs are usually combined with n-gram LMs via a fixed weighting based linear interpolation in state-of-the-art ASR systems. However, previous work doesn't fully exploit the difference of modelling power of the RNNLMs and n-gram LMs as n-gram level changes. In order to fully exploit the detailed n-gram level complementary attributes between the two LMs, a back-off based compact representation of n-gram dependent interpolation weights is proposed in this paper. This approach allows weight parameters to be robustly estimated on limited data. Experimental results are reported on the three tasks with varying amounts of training data. Small and consistent improvements in both perplexity and WER were obtained using the proposed interpolation approach over the baseline fixed weighting based linear interpolation." @default.
- W2770176249 created "2017-12-04" @default.
- W2770176249 creator A5002191410 @default.
- W2770176249 creator A5012703069 @default.
- W2770176249 creator A5015643912 @default.
- W2770176249 creator A5032000623 @default.
- W2770176249 date "2016-02-11" @default.
- W2770176249 modified "2023-09-24" @default.
- W2770176249 title "Investigation of Back-off Based Interpolation Between Recurrent Neural Network and N-gram Language Models (Author's Manuscript)" @default.
- W2770176249 hasPublicationYear "2016" @default.
- W2770176249 type Work @default.
- W2770176249 sameAs 2770176249 @default.
- W2770176249 citedByCount "0" @default.
- W2770176249 crossrefType "journal-article" @default.
- W2770176249 hasAuthorship W2770176249A5002191410 @default.
- W2770176249 hasAuthorship W2770176249A5012703069 @default.
- W2770176249 hasAuthorship W2770176249A5015643912 @default.
- W2770176249 hasAuthorship W2770176249A5032000623 @default.
- W2770176249 hasConcept C100279451 @default.
- W2770176249 hasConcept C11413529 @default.
- W2770176249 hasConcept C115961682 @default.
- W2770176249 hasConcept C126838900 @default.
- W2770176249 hasConcept C134306372 @default.
- W2770176249 hasConcept C137293760 @default.
- W2770176249 hasConcept C137800194 @default.
- W2770176249 hasConcept C153180895 @default.
- W2770176249 hasConcept C154945302 @default.
- W2770176249 hasConcept C165696696 @default.
- W2770176249 hasConcept C171836373 @default.
- W2770176249 hasConcept C177148314 @default.
- W2770176249 hasConcept C183115368 @default.
- W2770176249 hasConcept C28490314 @default.
- W2770176249 hasConcept C33923547 @default.
- W2770176249 hasConcept C38652104 @default.
- W2770176249 hasConcept C41008148 @default.
- W2770176249 hasConcept C50644808 @default.
- W2770176249 hasConcept C71924100 @default.
- W2770176249 hasConceptScore W2770176249C100279451 @default.
- W2770176249 hasConceptScore W2770176249C11413529 @default.
- W2770176249 hasConceptScore W2770176249C115961682 @default.
- W2770176249 hasConceptScore W2770176249C126838900 @default.
- W2770176249 hasConceptScore W2770176249C134306372 @default.
- W2770176249 hasConceptScore W2770176249C137293760 @default.
- W2770176249 hasConceptScore W2770176249C137800194 @default.
- W2770176249 hasConceptScore W2770176249C153180895 @default.
- W2770176249 hasConceptScore W2770176249C154945302 @default.
- W2770176249 hasConceptScore W2770176249C165696696 @default.
- W2770176249 hasConceptScore W2770176249C171836373 @default.
- W2770176249 hasConceptScore W2770176249C177148314 @default.
- W2770176249 hasConceptScore W2770176249C183115368 @default.
- W2770176249 hasConceptScore W2770176249C28490314 @default.
- W2770176249 hasConceptScore W2770176249C33923547 @default.
- W2770176249 hasConceptScore W2770176249C38652104 @default.
- W2770176249 hasConceptScore W2770176249C41008148 @default.
- W2770176249 hasConceptScore W2770176249C50644808 @default.
- W2770176249 hasConceptScore W2770176249C71924100 @default.
- W2770176249 hasLocation W27701762491 @default.
- W2770176249 hasOpenAccess W2770176249 @default.
- W2770176249 hasPrimaryLocation W27701762491 @default.
- W2770176249 hasRelatedWork W1585876329 @default.
- W2770176249 hasRelatedWork W1964742985 @default.
- W2770176249 hasRelatedWork W2139440170 @default.
- W2770176249 hasRelatedWork W2142390309 @default.
- W2770176249 hasRelatedWork W2217717732 @default.
- W2770176249 hasRelatedWork W2289003027 @default.
- W2770176249 hasRelatedWork W2466474295 @default.
- W2770176249 hasRelatedWork W2486205537 @default.
- W2770176249 hasRelatedWork W2742195102 @default.
- W2770176249 hasRelatedWork W2787142854 @default.
- W2770176249 hasRelatedWork W2800057634 @default.
- W2770176249 hasRelatedWork W2886180730 @default.
- W2770176249 hasRelatedWork W2886349653 @default.
- W2770176249 hasRelatedWork W2946280271 @default.
- W2770176249 hasRelatedWork W2964147652 @default.
- W2770176249 hasRelatedWork W2980874206 @default.
- W2770176249 hasRelatedWork W3016164858 @default.
- W2770176249 hasRelatedWork W3162587184 @default.
- W2770176249 hasRelatedWork W81231479 @default.
- W2770176249 hasRelatedWork W2890012642 @default.
- W2770176249 isParatext "false" @default.
- W2770176249 isRetracted "false" @default.
- W2770176249 magId "2770176249" @default.
- W2770176249 workType "article" @default.