Matches in SemOpenAlex for { <https://semopenalex.org/work/W2079362249> ?p ?o ?g. }
- W2079362249 endingPage "66" @default.
- W2079362249 startingPage "45" @default.
- W2079362249 abstract "We present a system that can separate and recognize the simultaneous speech of two people recorded in a single channel. Applied to the monaural speech separation and recognition challenge, the system out-performed all other participants – including human listeners – with an overall recognition error rate of 21.6%, compared to the human error rate of 22.3%. The system consists of a speaker recognizer, a model-based speech separation module, and a speech recognizer. For the separation models we explored a range of speech models that incorporate different levels of constraints on temporal dynamics to help infer the source speech signals. The system achieves its best performance when the model of temporal dynamics closely captures the grammatical constraints of the task. For inference, we compare a 2-D Viterbi algorithm and two loopy belief-propagation algorithms. We show how belief-propagation reduces the complexity of temporal inference from exponential to linear in the number of sources and the size of the language model. The best belief-propagation method results in nearly the same recognition error rate as exact inference." @default.
- W2079362249 created "2016-06-24" @default.
- W2079362249 creator A5037212510 @default.
- W2079362249 creator A5075577786 @default.
- W2079362249 creator A5082524152 @default.
- W2079362249 creator A5088753951 @default.
- W2079362249 date "2010-01-01" @default.
- W2079362249 modified "2023-10-16" @default.
- W2079362249 title "Super-human multi-talker speech recognition: A graphical modeling approach" @default.
- W2079362249 cites W123512928 @default.
- W2079362249 cites W174003511 @default.
- W2079362249 cites W2015143272 @default.
- W2079362249 cites W2016254085 @default.
- W2079362249 cites W2033178790 @default.
- W2079362249 cites W2045036776 @default.
- W2079362249 cites W2059833849 @default.
- W2079362249 cites W2060822897 @default.
- W2079362249 cites W2098387242 @default.
- W2079362249 cites W2100969003 @default.
- W2079362249 cites W2109886546 @default.
- W2079362249 cites W2130322773 @default.
- W2079362249 cites W2134383396 @default.
- W2079362249 cites W2137813581 @default.
- W2079362249 cites W2170120894 @default.
- W2079362249 cites W4245655784 @default.
- W2079362249 cites W44831635 @default.
- W2079362249 cites W80444264 @default.
- W2079362249 doi "https://doi.org/10.1016/j.csl.2008.11.001" @default.
- W2079362249 hasPublicationYear "2010" @default.
- W2079362249 type Work @default.
- W2079362249 sameAs 2079362249 @default.
- W2079362249 citedByCount "146" @default.
- W2079362249 countsByYear W20793622492012 @default.
- W2079362249 countsByYear W20793622492013 @default.
- W2079362249 countsByYear W20793622492014 @default.
- W2079362249 countsByYear W20793622492015 @default.
- W2079362249 countsByYear W20793622492016 @default.
- W2079362249 countsByYear W20793622492017 @default.
- W2079362249 countsByYear W20793622492018 @default.
- W2079362249 countsByYear W20793622492019 @default.
- W2079362249 countsByYear W20793622492020 @default.
- W2079362249 countsByYear W20793622492021 @default.
- W2079362249 countsByYear W20793622492022 @default.
- W2079362249 countsByYear W20793622492023 @default.
- W2079362249 crossrefType "journal-article" @default.
- W2079362249 hasAuthorship W2079362249A5037212510 @default.
- W2079362249 hasAuthorship W2079362249A5075577786 @default.
- W2079362249 hasAuthorship W2079362249A5082524152 @default.
- W2079362249 hasAuthorship W2079362249A5088753951 @default.
- W2079362249 hasConcept C102894143 @default.
- W2079362249 hasConcept C11413529 @default.
- W2079362249 hasConcept C137293760 @default.
- W2079362249 hasConcept C152948882 @default.
- W2079362249 hasConcept C153180895 @default.
- W2079362249 hasConcept C154945302 @default.
- W2079362249 hasConcept C155846161 @default.
- W2079362249 hasConcept C162324750 @default.
- W2079362249 hasConcept C187736073 @default.
- W2079362249 hasConcept C23224414 @default.
- W2079362249 hasConcept C2776214188 @default.
- W2079362249 hasConcept C2777472644 @default.
- W2079362249 hasConcept C2780451532 @default.
- W2079362249 hasConcept C28490314 @default.
- W2079362249 hasConcept C40969351 @default.
- W2079362249 hasConcept C41008148 @default.
- W2079362249 hasConcept C57273362 @default.
- W2079362249 hasConcept C60582962 @default.
- W2079362249 hasConcept C61328038 @default.
- W2079362249 hasConceptScore W2079362249C102894143 @default.
- W2079362249 hasConceptScore W2079362249C11413529 @default.
- W2079362249 hasConceptScore W2079362249C137293760 @default.
- W2079362249 hasConceptScore W2079362249C152948882 @default.
- W2079362249 hasConceptScore W2079362249C153180895 @default.
- W2079362249 hasConceptScore W2079362249C154945302 @default.
- W2079362249 hasConceptScore W2079362249C155846161 @default.
- W2079362249 hasConceptScore W2079362249C162324750 @default.
- W2079362249 hasConceptScore W2079362249C187736073 @default.
- W2079362249 hasConceptScore W2079362249C23224414 @default.
- W2079362249 hasConceptScore W2079362249C2776214188 @default.
- W2079362249 hasConceptScore W2079362249C2777472644 @default.
- W2079362249 hasConceptScore W2079362249C2780451532 @default.
- W2079362249 hasConceptScore W2079362249C28490314 @default.
- W2079362249 hasConceptScore W2079362249C40969351 @default.
- W2079362249 hasConceptScore W2079362249C41008148 @default.
- W2079362249 hasConceptScore W2079362249C57273362 @default.
- W2079362249 hasConceptScore W2079362249C60582962 @default.
- W2079362249 hasConceptScore W2079362249C61328038 @default.
- W2079362249 hasIssue "1" @default.
- W2079362249 hasLocation W20793622491 @default.
- W2079362249 hasOpenAccess W2079362249 @default.
- W2079362249 hasPrimaryLocation W20793622491 @default.
- W2079362249 hasRelatedWork W1520194733 @default.
- W2079362249 hasRelatedWork W2153267847 @default.
- W2079362249 hasRelatedWork W2501500329 @default.
- W2079362249 hasRelatedWork W2562956507 @default.
- W2079362249 hasRelatedWork W2962950510 @default.
- W2079362249 hasRelatedWork W3180766726 @default.
- W2079362249 hasRelatedWork W4286382505 @default.