Matches in SemOpenAlex for { <https://semopenalex.org/work/W2027964844> ?p ?o ?g. }
- W2027964844 abstract "In this paper we present an experimental study exploiting structural Bayesian adaptation for handling potential mismatches between training and test conditions for real-world applications to be realized in our multilingual very large vocabulary speech recognition (VLVSR) system project sponsored by MOTIE (The Ministry of Trade, Industry and Energy), Republic of Korea. The goal of the project is to construct a national-wide VLVSR cloud service platform for mobile applications. Besides system architecture design issues, at such a large scale, performance robustness problems, caused by mismatches in speakers, tasks, environments, and domains, etc., need to be taken into account very carefully as well. We decide to adopt adaptation, especially the structural MAP, techniques to reduce system accuracy degradation caused by these mismatches. Being part of an ongoing project, we describe how structural MAP approaches can be used for adaptation of both acoustic and language models for our VLVSR systems, and provide convincing experimental results to demonstrate how adaptation can be utilized to bridge the performance gap between the current state-of-the-art and deployable VLVSR systems." @default.
- W2027964844 created "2016-06-24" @default.
- W2027964844 creator A5012653576 @default.
- W2027964844 creator A5013118725 @default.
- W2027964844 creator A5038432784 @default.
- W2027964844 creator A5042721439 @default.
- W2027964844 creator A5064630603 @default.
- W2027964844 creator A5066868860 @default.
- W2027964844 creator A5079659476 @default.
- W2027964844 date "2013-10-01" @default.
- W2027964844 modified "2023-09-27" @default.
- W2027964844 title "An experimental study on structural-MAP approaches to implementing very large vocabulary speech recognition systems for real-world tasks" @default.
- W2027964844 cites W1480544121 @default.
- W2027964844 cites W1493946344 @default.
- W2027964844 cites W1533179050 @default.
- W2027964844 cites W1553004968 @default.
- W2027964844 cites W160901726 @default.
- W2027964844 cites W185360009 @default.
- W2027964844 cites W1966812932 @default.
- W2027964844 cites W1967558850 @default.
- W2027964844 cites W1973258741 @default.
- W2027964844 cites W1986695354 @default.
- W2027964844 cites W1996022519 @default.
- W2027964844 cites W2028629871 @default.
- W2027964844 cites W2075815989 @default.
- W2027964844 cites W2082474452 @default.
- W2027964844 cites W2086267546 @default.
- W2027964844 cites W2090755665 @default.
- W2027964844 cites W2097441502 @default.
- W2027964844 cites W2098692363 @default.
- W2027964844 cites W2099345940 @default.
- W2027964844 cites W2100506586 @default.
- W2027964844 cites W2100969003 @default.
- W2027964844 cites W2104687512 @default.
- W2027964844 cites W2110467295 @default.
- W2027964844 cites W2118714763 @default.
- W2027964844 cites W2124060484 @default.
- W2027964844 cites W2124776405 @default.
- W2027964844 cites W2125838338 @default.
- W2027964844 cites W2134237567 @default.
- W2027964844 cites W2135936685 @default.
- W2027964844 cites W2141133575 @default.
- W2027964844 cites W2141354973 @default.
- W2027964844 cites W2146871184 @default.
- W2027964844 cites W2147824816 @default.
- W2027964844 cites W2149175990 @default.
- W2027964844 cites W2158289097 @default.
- W2027964844 cites W2160246131 @default.
- W2027964844 cites W2160373860 @default.
- W2027964844 cites W2163680580 @default.
- W2027964844 cites W2164512012 @default.
- W2027964844 cites W2168171912 @default.
- W2027964844 cites W2178335482 @default.
- W2027964844 cites W22549796 @default.
- W2027964844 cites W2584852661 @default.
- W2027964844 cites W2950186769 @default.
- W2027964844 cites W3141839452 @default.
- W2027964844 cites W74241614 @default.
- W2027964844 cites W943204654 @default.
- W2027964844 cites W2074642696 @default.
- W2027964844 doi "https://doi.org/10.1109/apsipa.2013.6694185" @default.
- W2027964844 hasPublicationYear "2013" @default.
- W2027964844 type Work @default.
- W2027964844 sameAs 2027964844 @default.
- W2027964844 citedByCount "0" @default.
- W2027964844 crossrefType "proceedings-article" @default.
- W2027964844 hasAuthorship W2027964844A5012653576 @default.
- W2027964844 hasAuthorship W2027964844A5013118725 @default.
- W2027964844 hasAuthorship W2027964844A5038432784 @default.
- W2027964844 hasAuthorship W2027964844A5042721439 @default.
- W2027964844 hasAuthorship W2027964844A5064630603 @default.
- W2027964844 hasAuthorship W2027964844A5066868860 @default.
- W2027964844 hasAuthorship W2027964844A5079659476 @default.
- W2027964844 hasConcept C104317684 @default.
- W2027964844 hasConcept C119857082 @default.
- W2027964844 hasConcept C120665830 @default.
- W2027964844 hasConcept C121332964 @default.
- W2027964844 hasConcept C123657996 @default.
- W2027964844 hasConcept C138885662 @default.
- W2027964844 hasConcept C139807058 @default.
- W2027964844 hasConcept C142362112 @default.
- W2027964844 hasConcept C153349607 @default.
- W2027964844 hasConcept C154945302 @default.
- W2027964844 hasConcept C185592680 @default.
- W2027964844 hasConcept C23224414 @default.
- W2027964844 hasConcept C2777601683 @default.
- W2027964844 hasConcept C41008148 @default.
- W2027964844 hasConcept C41895202 @default.
- W2027964844 hasConcept C55493867 @default.
- W2027964844 hasConcept C63479239 @default.
- W2027964844 hasConceptScore W2027964844C104317684 @default.
- W2027964844 hasConceptScore W2027964844C119857082 @default.
- W2027964844 hasConceptScore W2027964844C120665830 @default.
- W2027964844 hasConceptScore W2027964844C121332964 @default.
- W2027964844 hasConceptScore W2027964844C123657996 @default.
- W2027964844 hasConceptScore W2027964844C138885662 @default.
- W2027964844 hasConceptScore W2027964844C139807058 @default.
- W2027964844 hasConceptScore W2027964844C142362112 @default.
- W2027964844 hasConceptScore W2027964844C153349607 @default.
- W2027964844 hasConceptScore W2027964844C154945302 @default.