Matches in SemOpenAlex for { <https://semopenalex.org/work/W2625701092> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2625701092 abstract "Speech recognition systems for irregularly-spelled languages like English normally require hand-written pronunciations. In this paper, we describe a system for automatically obtaining pronunciations of words for which pronunciations are not available, but for which transcribed data exists. Our method integrates information from the letter sequence and from the acoustic evidence. The novel aspect of the problem that we address is the problem of how to prune entries from such a lexicon (since, empirically, lexicons with too many entries do not tend to be good for ASR performance). Experiments on various ASR tasks show that, with the proposed framework, starting with an initial lexicon of several thousand words, we are able to learn a lexicon which performs close to a full expert lexicon in terms of WER performance on test data, and is better than lexicons built using G2P alone or with a pruning criterion based on pronunciation probability." @default.
- W2625701092 created "2017-06-23" @default.
- W2625701092 creator A5014580424 @default.
- W2625701092 creator A5028956985 @default.
- W2625701092 creator A5061407928 @default.
- W2625701092 creator A5084286453 @default.
- W2625701092 date "2017-06-12" @default.
- W2625701092 modified "2023-09-26" @default.
- W2625701092 title "Acoustic data-driven lexicon learning based on a greedy pronunciation selection framework" @default.
- W2625701092 cites W1494198834 @default.
- W2625701092 cites W1506752962 @default.
- W2625701092 cites W1524333225 @default.
- W2625701092 cites W1565662837 @default.
- W2625701092 cites W1778492285 @default.
- W2625701092 cites W1974974326 @default.
- W2625701092 cites W2047497400 @default.
- W2625701092 cites W2050526637 @default.
- W2625701092 cites W2132991150 @default.
- W2625701092 cites W2250357346 @default.
- W2625701092 cites W2294752925 @default.
- W2625701092 cites W2398867685 @default.
- W2625701092 cites W2402146185 @default.
- W2625701092 cites W2510428086 @default.
- W2625701092 cites W2514741789 @default.
- W2625701092 cites W7052673 @default.
- W2625701092 doi "https://doi.org/10.48550/arxiv.1706.03747" @default.
- W2625701092 hasPublicationYear "2017" @default.
- W2625701092 type Work @default.
- W2625701092 sameAs 2625701092 @default.
- W2625701092 citedByCount "5" @default.
- W2625701092 countsByYear W26257010922018 @default.
- W2625701092 countsByYear W26257010922019 @default.
- W2625701092 countsByYear W26257010922020 @default.
- W2625701092 countsByYear W26257010922021 @default.
- W2625701092 crossrefType "posted-content" @default.
- W2625701092 hasAuthorship W2625701092A5014580424 @default.
- W2625701092 hasAuthorship W2625701092A5028956985 @default.
- W2625701092 hasAuthorship W2625701092A5061407928 @default.
- W2625701092 hasAuthorship W2625701092A5084286453 @default.
- W2625701092 hasBestOaLocation W26257010921 @default.
- W2625701092 hasConcept C108010975 @default.
- W2625701092 hasConcept C138885662 @default.
- W2625701092 hasConcept C154945302 @default.
- W2625701092 hasConcept C204321447 @default.
- W2625701092 hasConcept C2778112365 @default.
- W2625701092 hasConcept C2778121359 @default.
- W2625701092 hasConcept C2780844864 @default.
- W2625701092 hasConcept C28490314 @default.
- W2625701092 hasConcept C41008148 @default.
- W2625701092 hasConcept C41895202 @default.
- W2625701092 hasConcept C54355233 @default.
- W2625701092 hasConcept C6557445 @default.
- W2625701092 hasConcept C81917197 @default.
- W2625701092 hasConcept C86803240 @default.
- W2625701092 hasConceptScore W2625701092C108010975 @default.
- W2625701092 hasConceptScore W2625701092C138885662 @default.
- W2625701092 hasConceptScore W2625701092C154945302 @default.
- W2625701092 hasConceptScore W2625701092C204321447 @default.
- W2625701092 hasConceptScore W2625701092C2778112365 @default.
- W2625701092 hasConceptScore W2625701092C2778121359 @default.
- W2625701092 hasConceptScore W2625701092C2780844864 @default.
- W2625701092 hasConceptScore W2625701092C28490314 @default.
- W2625701092 hasConceptScore W2625701092C41008148 @default.
- W2625701092 hasConceptScore W2625701092C41895202 @default.
- W2625701092 hasConceptScore W2625701092C54355233 @default.
- W2625701092 hasConceptScore W2625701092C6557445 @default.
- W2625701092 hasConceptScore W2625701092C81917197 @default.
- W2625701092 hasConceptScore W2625701092C86803240 @default.
- W2625701092 hasLocation W26257010921 @default.
- W2625701092 hasOpenAccess W2625701092 @default.
- W2625701092 hasPrimaryLocation W26257010921 @default.
- W2625701092 hasRelatedWork W1529136209 @default.
- W2625701092 hasRelatedWork W2097473479 @default.
- W2625701092 hasRelatedWork W2133824618 @default.
- W2625701092 hasRelatedWork W2136869290 @default.
- W2625701092 hasRelatedWork W2398867685 @default.
- W2625701092 hasRelatedWork W2604904674 @default.
- W2625701092 hasRelatedWork W2625701092 @default.
- W2625701092 hasRelatedWork W2734655221 @default.
- W2625701092 hasRelatedWork W2963573574 @default.
- W2625701092 hasRelatedWork W88309612 @default.
- W2625701092 isParatext "false" @default.
- W2625701092 isRetracted "false" @default.
- W2625701092 magId "2625701092" @default.
- W2625701092 workType "article" @default.