Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312096440> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4312096440 abstract "Active research has been conducted of Spoken Term Detection (STD), which uses text queries (search words) to seek specific scenes in large amounts of data, including audio data. In subword-to-subword and state-to-state matching using results of automatic speech recognizer (ASR) for speech data, if a query includes an out-of-vocabulary (OOV) word that does not exist in the lexicon of ASR, retrieval accuracy deterioration occurs. Frame-level matching performs more detailed matching at the frame level using a maximum likelihood series that arranges the most probable states for each frame of the posterior probability vector, which is the output of a Deep Neural Network (DNN) used as an acoustic model for ASR, whereas subword-to-subword or state-to-state uses preconstructed acoustic distances between subwords or states. For query by example (QbE), which uses spoken queries, high retrieval accuracy is obtained using the posterior probability vector of speech data. As described herein, we propose a new frame-level matching scheme for a text query using the posterior probabilities of speech data instead of the preconstructed acoustic distance between subwords of states. Thereby, the retrieval accuracy is improved. Machine learning models of two types with different numbers of states are introduced to improve the retrieval accuracy further. Because each model shows different retrieval results, integration of these models is expected to be mutually complementary, thereby improving the retrieval accuracy. Experiments were conducted using public test collections of the SpokenDoc task from NTCIR-10 and NTCIR-12 workshops as benchmarks. Results indicate that the proposed method outperforms the best accuracy obtained at the workshop by 26.95 points for NTCIR-10 and 4.44 points for NTCIR-12. These results demonstrate the effectiveness of the proposed method." @default.
- W4312096440 created "2023-01-04" @default.
- W4312096440 creator A5035354644 @default.
- W4312096440 creator A5052973866 @default.
- W4312096440 creator A5065614961 @default.
- W4312096440 creator A5071262282 @default.
- W4312096440 date "2022-11-07" @default.
- W4312096440 modified "2023-10-16" @default.
- W4312096440 title "Frame-Level Matching Scheme Using Posteriorgram Probability Distance of Spoken Data to Improve Search Accuracy of Spoken Term Detection" @default.
- W4312096440 cites W1540624770 @default.
- W4312096440 cites W2126203737 @default.
- W4312096440 cites W2514342258 @default.
- W4312096440 cites W2748147793 @default.
- W4312096440 cites W2766219058 @default.
- W4312096440 cites W294738100 @default.
- W4312096440 cites W2962780374 @default.
- W4312096440 cites W3012147781 @default.
- W4312096440 doi "https://doi.org/10.23919/apsipaasc55919.2022.9980177" @default.
- W4312096440 hasPublicationYear "2022" @default.
- W4312096440 type Work @default.
- W4312096440 citedByCount "0" @default.
- W4312096440 crossrefType "proceedings-article" @default.
- W4312096440 hasAuthorship W4312096440A5035354644 @default.
- W4312096440 hasAuthorship W4312096440A5052973866 @default.
- W4312096440 hasAuthorship W4312096440A5065614961 @default.
- W4312096440 hasAuthorship W4312096440A5071262282 @default.
- W4312096440 hasConcept C105795698 @default.
- W4312096440 hasConcept C107673813 @default.
- W4312096440 hasConcept C121332964 @default.
- W4312096440 hasConcept C126042441 @default.
- W4312096440 hasConcept C138885662 @default.
- W4312096440 hasConcept C153180895 @default.
- W4312096440 hasConcept C154945302 @default.
- W4312096440 hasConcept C165064840 @default.
- W4312096440 hasConcept C16910744 @default.
- W4312096440 hasConcept C199360897 @default.
- W4312096440 hasConcept C204321447 @default.
- W4312096440 hasConcept C28490314 @default.
- W4312096440 hasConcept C33923547 @default.
- W4312096440 hasConcept C41008148 @default.
- W4312096440 hasConcept C41895202 @default.
- W4312096440 hasConcept C57830394 @default.
- W4312096440 hasConcept C61797465 @default.
- W4312096440 hasConcept C62520636 @default.
- W4312096440 hasConcept C76155785 @default.
- W4312096440 hasConcept C90805587 @default.
- W4312096440 hasConceptScore W4312096440C105795698 @default.
- W4312096440 hasConceptScore W4312096440C107673813 @default.
- W4312096440 hasConceptScore W4312096440C121332964 @default.
- W4312096440 hasConceptScore W4312096440C126042441 @default.
- W4312096440 hasConceptScore W4312096440C138885662 @default.
- W4312096440 hasConceptScore W4312096440C153180895 @default.
- W4312096440 hasConceptScore W4312096440C154945302 @default.
- W4312096440 hasConceptScore W4312096440C165064840 @default.
- W4312096440 hasConceptScore W4312096440C16910744 @default.
- W4312096440 hasConceptScore W4312096440C199360897 @default.
- W4312096440 hasConceptScore W4312096440C204321447 @default.
- W4312096440 hasConceptScore W4312096440C28490314 @default.
- W4312096440 hasConceptScore W4312096440C33923547 @default.
- W4312096440 hasConceptScore W4312096440C41008148 @default.
- W4312096440 hasConceptScore W4312096440C41895202 @default.
- W4312096440 hasConceptScore W4312096440C57830394 @default.
- W4312096440 hasConceptScore W4312096440C61797465 @default.
- W4312096440 hasConceptScore W4312096440C62520636 @default.
- W4312096440 hasConceptScore W4312096440C76155785 @default.
- W4312096440 hasConceptScore W4312096440C90805587 @default.
- W4312096440 hasLocation W43120964401 @default.
- W4312096440 hasOpenAccess W4312096440 @default.
- W4312096440 hasPrimaryLocation W43120964401 @default.
- W4312096440 hasRelatedWork W1979777211 @default.
- W4312096440 hasRelatedWork W2099911662 @default.
- W4312096440 hasRelatedWork W2102298087 @default.
- W4312096440 hasRelatedWork W2141735610 @default.
- W4312096440 hasRelatedWork W2360025963 @default.
- W4312096440 hasRelatedWork W2786018489 @default.
- W4312096440 hasRelatedWork W3040010296 @default.
- W4312096440 hasRelatedWork W3107474891 @default.
- W4312096440 hasRelatedWork W4312096440 @default.
- W4312096440 hasRelatedWork W67997247 @default.
- W4312096440 isParatext "false" @default.
- W4312096440 isRetracted "false" @default.
- W4312096440 workType "article" @default.