Matches in SemOpenAlex for { <https://semopenalex.org/work/W2137079242> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2137079242 abstract "We consider how to optimize the acoustic features used by hidden Markov models (HMMs) for automatic speech recognition (ASR). We investigate a mistake-driven algorithm that discriminatively reweights the acoustic features in order to separate the log-likelihoods of correct and incorrect transcriptions by a large margin. The algorithm simultaneously optimizes the HMM parameters in the back end by adapting them to the reweighted features computed by the front end. Using an online approach, we incrementally update feature weights and model parameters after the decoding of each training utterance. To mitigate the strongly biased gradients from individual training utterances, we train several different recognizers in parallel while tying the feature transformations in their front ends. We show that this parameter-tying across different recognizers leads to more stable updates and generally fewer recognition errors." @default.
- W2137079242 created "2016-06-24" @default.
- W2137079242 creator A5021516103 @default.
- W2137079242 creator A5029087418 @default.
- W2137079242 creator A5059411202 @default.
- W2137079242 date "2009-12-01" @default.
- W2137079242 modified "2023-10-18" @default.
- W2137079242 title "Large-margin feature adaptation for automatic speech recognition" @default.
- W2137079242 cites W112175133 @default.
- W2137079242 cites W145744102 @default.
- W2137079242 cites W1481751294 @default.
- W2137079242 cites W1507239162 @default.
- W2137079242 cites W1553271421 @default.
- W2137079242 cites W1560013842 @default.
- W2137079242 cites W170098597 @default.
- W2137079242 cites W1877570817 @default.
- W2137079242 cites W1970500656 @default.
- W2137079242 cites W2000626086 @default.
- W2137079242 cites W2002342963 @default.
- W2137079242 cites W2008652694 @default.
- W2137079242 cites W2022768064 @default.
- W2137079242 cites W2044145689 @default.
- W2137079242 cites W2044223162 @default.
- W2137079242 cites W2063541597 @default.
- W2137079242 cites W2077804127 @default.
- W2137079242 cites W2104448323 @default.
- W2137079242 cites W2125234026 @default.
- W2137079242 cites W2132215870 @default.
- W2137079242 cites W43454013 @default.
- W2137079242 cites W81836371 @default.
- W2137079242 doi "https://doi.org/10.1109/asru.2009.5373320" @default.
- W2137079242 hasPublicationYear "2009" @default.
- W2137079242 type Work @default.
- W2137079242 sameAs 2137079242 @default.
- W2137079242 citedByCount "2" @default.
- W2137079242 countsByYear W21370792422013 @default.
- W2137079242 crossrefType "proceedings-article" @default.
- W2137079242 hasAuthorship W2137079242A5021516103 @default.
- W2137079242 hasAuthorship W2137079242A5029087418 @default.
- W2137079242 hasAuthorship W2137079242A5059411202 @default.
- W2137079242 hasBestOaLocation W21370792422 @default.
- W2137079242 hasConcept C11413529 @default.
- W2137079242 hasConcept C119857082 @default.
- W2137079242 hasConcept C138885662 @default.
- W2137079242 hasConcept C153180895 @default.
- W2137079242 hasConcept C154945302 @default.
- W2137079242 hasConcept C23224414 @default.
- W2137079242 hasConcept C2775852435 @default.
- W2137079242 hasConcept C2776401178 @default.
- W2137079242 hasConcept C28490314 @default.
- W2137079242 hasConcept C41008148 @default.
- W2137079242 hasConcept C41895202 @default.
- W2137079242 hasConcept C57273362 @default.
- W2137079242 hasConcept C774472 @default.
- W2137079242 hasConceptScore W2137079242C11413529 @default.
- W2137079242 hasConceptScore W2137079242C119857082 @default.
- W2137079242 hasConceptScore W2137079242C138885662 @default.
- W2137079242 hasConceptScore W2137079242C153180895 @default.
- W2137079242 hasConceptScore W2137079242C154945302 @default.
- W2137079242 hasConceptScore W2137079242C23224414 @default.
- W2137079242 hasConceptScore W2137079242C2775852435 @default.
- W2137079242 hasConceptScore W2137079242C2776401178 @default.
- W2137079242 hasConceptScore W2137079242C28490314 @default.
- W2137079242 hasConceptScore W2137079242C41008148 @default.
- W2137079242 hasConceptScore W2137079242C41895202 @default.
- W2137079242 hasConceptScore W2137079242C57273362 @default.
- W2137079242 hasConceptScore W2137079242C774472 @default.
- W2137079242 hasLocation W21370792421 @default.
- W2137079242 hasLocation W21370792422 @default.
- W2137079242 hasOpenAccess W2137079242 @default.
- W2137079242 hasPrimaryLocation W21370792421 @default.
- W2137079242 hasRelatedWork W1966737826 @default.
- W2137079242 hasRelatedWork W2012060148 @default.
- W2137079242 hasRelatedWork W2058877998 @default.
- W2137079242 hasRelatedWork W2137079242 @default.
- W2137079242 hasRelatedWork W2137833003 @default.
- W2137079242 hasRelatedWork W2225817525 @default.
- W2137079242 hasRelatedWork W2375321655 @default.
- W2137079242 hasRelatedWork W2540351954 @default.
- W2137079242 hasRelatedWork W2739991629 @default.
- W2137079242 hasRelatedWork W60887625 @default.
- W2137079242 isParatext "false" @default.
- W2137079242 isRetracted "false" @default.
- W2137079242 magId "2137079242" @default.
- W2137079242 workType "article" @default.