Matches in SemOpenAlex for { <https://semopenalex.org/work/W2203545501> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2203545501 endingPage "129" @default.
- W2203545501 startingPage "126" @default.
- W2203545501 abstract "The synchronization of text transcripts with audio tracks is typically solved by forced alignment at the phonetic level. However, when dealing with either very long audio tracks or acoustically inaccurate text transcripts, more complex methods are needed, usually based on heavy and costly ASR systems. In a previous work, we showed that a simple and lightweight method could be effectively applied, based on a free phonetic decoding of the speech signal and the alignment of the free and reference phonetic sequences, allowing the transfer of timestamps from the former to the latter. This method has yielded competitive results on the Hub4-97 dataset and is currently applied to synchronize the videos and minutes of the Basque Parliament plenary sessions. In this paper, probabilistic kernels (similarity functions) are applied, based on the hypothesis that a confusion matrix computed from a large corpus of speech conveys key information about the behavior of the phonetic decoder, and that the probabilistic interpretation of this information may help design informative kernels leading to improved alignments. The probabilistic kernels proposed in this work outperform our baseline kernels and other alternatives, including a reference ASR-based approach and a knowledge-based kernel, in experiments on the Hub4-97 dataset." @default.
- W2203545501 created "2016-06-24" @default.
- W2203545501 creator A5031896364 @default.
- W2203545501 creator A5057476491 @default.
- W2203545501 creator A5063619413 @default.
- W2203545501 creator A5067184681 @default.
- W2203545501 creator A5084820966 @default.
- W2203545501 date "2016-01-01" @default.
- W2203545501 modified "2023-09-26" @default.
- W2203545501 title "Probabilistic Kernels for Improved Text-to-Speech Alignment in Long Audio Tracks" @default.
- W2203545501 cites W123891035 @default.
- W2203545501 cites W1245895196 @default.
- W2203545501 cites W1549877291 @default.
- W2203545501 cites W2015412875 @default.
- W2203545501 cites W2105961775 @default.
- W2203545501 cites W2165654401 @default.
- W2203545501 cites W2293596383 @default.
- W2203545501 cites W2397159106 @default.
- W2203545501 doi "https://doi.org/10.1109/lsp.2015.2505140" @default.
- W2203545501 hasPublicationYear "2016" @default.
- W2203545501 type Work @default.
- W2203545501 sameAs 2203545501 @default.
- W2203545501 citedByCount "11" @default.
- W2203545501 countsByYear W22035455012017 @default.
- W2203545501 countsByYear W22035455012018 @default.
- W2203545501 countsByYear W22035455012019 @default.
- W2203545501 countsByYear W22035455012020 @default.
- W2203545501 countsByYear W22035455012021 @default.
- W2203545501 countsByYear W22035455012022 @default.
- W2203545501 countsByYear W22035455012023 @default.
- W2203545501 crossrefType "journal-article" @default.
- W2203545501 hasAuthorship W2203545501A5031896364 @default.
- W2203545501 hasAuthorship W2203545501A5057476491 @default.
- W2203545501 hasAuthorship W2203545501A5063619413 @default.
- W2203545501 hasAuthorship W2203545501A5067184681 @default.
- W2203545501 hasAuthorship W2203545501A5084820966 @default.
- W2203545501 hasConcept C113954288 @default.
- W2203545501 hasConcept C11413529 @default.
- W2203545501 hasConcept C114614502 @default.
- W2203545501 hasConcept C127162648 @default.
- W2203545501 hasConcept C153180895 @default.
- W2203545501 hasConcept C154945302 @default.
- W2203545501 hasConcept C2778562939 @default.
- W2203545501 hasConcept C28490314 @default.
- W2203545501 hasConcept C31258907 @default.
- W2203545501 hasConcept C33923547 @default.
- W2203545501 hasConcept C38652104 @default.
- W2203545501 hasConcept C41008148 @default.
- W2203545501 hasConcept C49937458 @default.
- W2203545501 hasConcept C57273362 @default.
- W2203545501 hasConcept C74193536 @default.
- W2203545501 hasConceptScore W2203545501C113954288 @default.
- W2203545501 hasConceptScore W2203545501C11413529 @default.
- W2203545501 hasConceptScore W2203545501C114614502 @default.
- W2203545501 hasConceptScore W2203545501C127162648 @default.
- W2203545501 hasConceptScore W2203545501C153180895 @default.
- W2203545501 hasConceptScore W2203545501C154945302 @default.
- W2203545501 hasConceptScore W2203545501C2778562939 @default.
- W2203545501 hasConceptScore W2203545501C28490314 @default.
- W2203545501 hasConceptScore W2203545501C31258907 @default.
- W2203545501 hasConceptScore W2203545501C33923547 @default.
- W2203545501 hasConceptScore W2203545501C38652104 @default.
- W2203545501 hasConceptScore W2203545501C41008148 @default.
- W2203545501 hasConceptScore W2203545501C49937458 @default.
- W2203545501 hasConceptScore W2203545501C57273362 @default.
- W2203545501 hasConceptScore W2203545501C74193536 @default.
- W2203545501 hasIssue "1" @default.
- W2203545501 hasLocation W22035455011 @default.
- W2203545501 hasOpenAccess W2203545501 @default.
- W2203545501 hasPrimaryLocation W22035455011 @default.
- W2203545501 hasRelatedWork W2046904092 @default.
- W2203545501 hasRelatedWork W2076520961 @default.
- W2203545501 hasRelatedWork W2110459882 @default.
- W2203545501 hasRelatedWork W2118043379 @default.
- W2203545501 hasRelatedWork W2141018987 @default.
- W2203545501 hasRelatedWork W2151022383 @default.
- W2203545501 hasRelatedWork W2348964713 @default.
- W2203545501 hasRelatedWork W2352517023 @default.
- W2203545501 hasRelatedWork W2377216019 @default.
- W2203545501 hasRelatedWork W2897194639 @default.
- W2203545501 hasVolume "23" @default.
- W2203545501 isParatext "false" @default.
- W2203545501 isRetracted "false" @default.
- W2203545501 magId "2203545501" @default.
- W2203545501 workType "article" @default.