Matches in SemOpenAlex for { <https://semopenalex.org/work/W2185814970> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2185814970 abstract "This paper presents the application of Neural Network Bottleneck (BN) features in Language Identification (LID). BN f eatures are generally used for Large Vocabulary Speech Recognition in conjunction with conventional acoustic features, s uch as MFCC or PLP. We compare the BN features to several common types of acoustic features used in the state-of-the-art LID systems. The test set is from DARPA RATS (Robust Automatic Transcription of Speech) program, which seeks to advance state-of-the-art detection capabilities on audio from hig hly degraded radio communication channels. On this type of noisy data, we show that in average, the BN features provide a 45% relative improvement in the Cavgor Equal Error Rate (EER) metrics across several test duration conditions, with resp ect to our single best acoustic features. Index Terms: language identification, noisy speech, robust feature extraction" @default.
- W2185814970 created "2016-06-24" @default.
- W2185814970 creator A5002029078 @default.
- W2185814970 creator A5008717681 @default.
- W2185814970 creator A5021019207 @default.
- W2185814970 creator A5045473616 @default.
- W2185814970 creator A5047596805 @default.
- W2185814970 creator A5076315361 @default.
- W2185814970 creator A5088097858 @default.
- W2185814970 creator A5088966231 @default.
- W2185814970 date "2014-06-16" @default.
- W2185814970 modified "2023-10-01" @default.
- W2185814970 title "Neural Network Bottleneck Features for Language Identification" @default.
- W2185814970 cites W156237177 @default.
- W2185814970 cites W162588823 @default.
- W2185814970 cites W2015138456 @default.
- W2185814970 cites W2026704977 @default.
- W2185814970 cites W204053250 @default.
- W2185814970 cites W2072349636 @default.
- W2185814970 cites W2074262827 @default.
- W2185814970 cites W2091326689 @default.
- W2185814970 cites W2099424804 @default.
- W2185814970 cites W2114782757 @default.
- W2185814970 cites W2128391065 @default.
- W2185814970 cites W2146194791 @default.
- W2185814970 cites W2146635662 @default.
- W2185814970 cites W2147676440 @default.
- W2185814970 cites W2150769028 @default.
- W2185814970 cites W2395544453 @default.
- W2185814970 cites W2399270979 @default.
- W2185814970 cites W2403186097 @default.
- W2185814970 cites W2405584646 @default.
- W2185814970 cites W307699962 @default.
- W2185814970 cites W70590613 @default.
- W2185814970 doi "https://doi.org/10.21437/odyssey.2014-45" @default.
- W2185814970 hasPublicationYear "2014" @default.
- W2185814970 type Work @default.
- W2185814970 sameAs 2185814970 @default.
- W2185814970 citedByCount "61" @default.
- W2185814970 countsByYear W21858149702015 @default.
- W2185814970 countsByYear W21858149702016 @default.
- W2185814970 countsByYear W21858149702017 @default.
- W2185814970 countsByYear W21858149702018 @default.
- W2185814970 countsByYear W21858149702019 @default.
- W2185814970 countsByYear W21858149702020 @default.
- W2185814970 countsByYear W21858149702021 @default.
- W2185814970 countsByYear W21858149702022 @default.
- W2185814970 countsByYear W21858149702023 @default.
- W2185814970 crossrefType "proceedings-article" @default.
- W2185814970 hasAuthorship W2185814970A5002029078 @default.
- W2185814970 hasAuthorship W2185814970A5008717681 @default.
- W2185814970 hasAuthorship W2185814970A5021019207 @default.
- W2185814970 hasAuthorship W2185814970A5045473616 @default.
- W2185814970 hasAuthorship W2185814970A5047596805 @default.
- W2185814970 hasAuthorship W2185814970A5076315361 @default.
- W2185814970 hasAuthorship W2185814970A5088097858 @default.
- W2185814970 hasAuthorship W2185814970A5088966231 @default.
- W2185814970 hasConcept C116834253 @default.
- W2185814970 hasConcept C149635348 @default.
- W2185814970 hasConcept C154945302 @default.
- W2185814970 hasConcept C204321447 @default.
- W2185814970 hasConcept C2780513914 @default.
- W2185814970 hasConcept C41008148 @default.
- W2185814970 hasConcept C50644808 @default.
- W2185814970 hasConcept C59822182 @default.
- W2185814970 hasConcept C86803240 @default.
- W2185814970 hasConceptScore W2185814970C116834253 @default.
- W2185814970 hasConceptScore W2185814970C149635348 @default.
- W2185814970 hasConceptScore W2185814970C154945302 @default.
- W2185814970 hasConceptScore W2185814970C204321447 @default.
- W2185814970 hasConceptScore W2185814970C2780513914 @default.
- W2185814970 hasConceptScore W2185814970C41008148 @default.
- W2185814970 hasConceptScore W2185814970C50644808 @default.
- W2185814970 hasConceptScore W2185814970C59822182 @default.
- W2185814970 hasConceptScore W2185814970C86803240 @default.
- W2185814970 hasLocation W21858149701 @default.
- W2185814970 hasOpenAccess W2185814970 @default.
- W2185814970 hasPrimaryLocation W21858149701 @default.
- W2185814970 hasRelatedWork W2087937280 @default.
- W2185814970 hasRelatedWork W2353647904 @default.
- W2185814970 hasRelatedWork W2354251581 @default.
- W2185814970 hasRelatedWork W2357461155 @default.
- W2185814970 hasRelatedWork W2384129116 @default.
- W2185814970 hasRelatedWork W2607965789 @default.
- W2185814970 hasRelatedWork W2766721049 @default.
- W2185814970 hasRelatedWork W3045908633 @default.
- W2185814970 hasRelatedWork W3145924829 @default.
- W2185814970 hasRelatedWork W3152267458 @default.
- W2185814970 isParatext "false" @default.
- W2185814970 isRetracted "false" @default.
- W2185814970 magId "2185814970" @default.
- W2185814970 workType "article" @default.