Matches in SemOpenAlex for { <https://semopenalex.org/work/W157668738> ?p ?o ?g. }
Showing items 1 to 51 of
51
with 100 items per page.
- W157668738 abstract "This paper presents a new architecture for automatic continuous speech recognition called HEAR - Hybrid Episodic-Abstract speech Recognizer. HEAR relies on both parametric speech models (HMMs) and episodic memory. We propose an evaluation on the Wall Street Journal corpus, a standard continuous speech recognition task, and compare the results with a state-of-the-art HMM baseline. HEAR is shown to be a viable and a competitive architecture. While the HMMs have been studied and optimized during decades, their performance seems to converge to a limit which is lower than human performance. On the contrary, episodic memory modeling for speech recognition as applied in HEAR offers flexibility to enrich the recognizer with information the HMMs lack. This opportunity as well as future work are exposed in a discussion." @default.
- W157668738 created "2016-06-24" @default.
- W157668738 creator A5041039488 @default.
- W157668738 creator A5069817284 @default.
- W157668738 date "2009-09-06" @default.
- W157668738 modified "2023-09-24" @default.
- W157668738 title "HEAR: an hybrid episodic-abstract speech recognizer" @default.
- W157668738 cites W1494243555 @default.
- W157668738 cites W1746705224 @default.
- W157668738 cites W196401904 @default.
- W157668738 cites W2008501847 @default.
- W157668738 cites W2082385556 @default.
- W157668738 cites W2095959744 @default.
- W157668738 cites W2096303239 @default.
- W157668738 cites W2097207027 @default.
- W157668738 cites W2150389998 @default.
- W157668738 cites W65465483 @default.
- W157668738 cites W2113601991 @default.
- W157668738 doi "https://doi.org/10.21437/interspeech.2009-570" @default.
- W157668738 hasPublicationYear "2009" @default.
- W157668738 type Work @default.
- W157668738 sameAs 157668738 @default.
- W157668738 citedByCount "5" @default.
- W157668738 crossrefType "proceedings-article" @default.
- W157668738 hasAuthorship W157668738A5041039488 @default.
- W157668738 hasAuthorship W157668738A5069817284 @default.
- W157668738 hasConcept C154945302 @default.
- W157668738 hasConcept C204321447 @default.
- W157668738 hasConcept C28490314 @default.
- W157668738 hasConcept C41008148 @default.
- W157668738 hasConceptScore W157668738C154945302 @default.
- W157668738 hasConceptScore W157668738C204321447 @default.
- W157668738 hasConceptScore W157668738C28490314 @default.
- W157668738 hasConceptScore W157668738C41008148 @default.
- W157668738 hasLocation W1576687381 @default.
- W157668738 hasOpenAccess W157668738 @default.
- W157668738 hasPrimaryLocation W1576687381 @default.
- W157668738 hasRelatedWork W1552159754 @default.
- W157668738 hasRelatedWork W2131420137 @default.
- W157668738 hasRelatedWork W2148757832 @default.
- W157668738 hasRelatedWork W2293457016 @default.
- W157668738 hasRelatedWork W2368651715 @default.
- W157668738 hasRelatedWork W2611614995 @default.
- W157668738 hasRelatedWork W2789919619 @default.
- W157668738 hasRelatedWork W3107474891 @default.
- W157668738 hasRelatedWork W3169305685 @default.
- W157668738 hasRelatedWork W4321496520 @default.
- W157668738 isParatext "false" @default.
- W157668738 isRetracted "false" @default.
- W157668738 magId "157668738" @default.
- W157668738 workType "article" @default.