FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W69897880> ?p ?o ?g. }

• W69897880 abstract "The modern proliferation of very large audio and video databases has created a need for effective methods of indexing and searching highly variable or uncertain data. Classical search and indexing algorithms deal with clean input sequences. However, an index created from speech or transcriptions is marked with errors and uncertainties stemming from the use of imperfect statistical models in the transcription process. This thesis presents novel algorithms, analyses, and general techniques and tools for effective indexing and search that not only tolerate but exploit this uncertainty.We have devised a new identification technique in which each song is represented by a distinct sequence of sounds, called music phonemes. We learn the set of phonemes, as well as a unique sequence of phonemes characterizing each song, using an unsupervised algorithm. We also create a compact mapping of phoneme sequences to songs. Using these techniques, we construct an efficient and robust large-scale identification system.We have further designed new algorithms for compact indexing of uncertain inputs based on suffix and factor automata and given novel theoretical guarantees for their space requirements. We show that the suffix automaton or factor automaton of a set of strings U has at most 2Q - 2 states, where Q is the number of nodes of a prefix-tree representing the strings in U. We also describe matching new linear-time algorithms for constructing the suffix automaton S or factor automaton F of U in time O(|S|).We have also defined a new quality measure for topic segmentation systems and designed a discriminative topic segmentation algorithm for speech inputs. The new quality measure improves on previously used criteria and is correlated with human judgment of topic-coherence. Our segmentation algorithm uses a novel general topical similarity score based on word co-occurrences. This new algorithm outperforms previous methods in experiments over speech and text streams. We further demonstrate that the performance of segmentation algorithms can be improved by using a lattice of competing hypotheses over the speech stream rather than just the one-best hypothesis as input." @default.
• W69897880 created "2016-06-24" @default.
• W69897880 creator A5058585526 @default.
• W69897880 creator A5058849006 @default.
• W69897880 date "2009-01-01" @default.
• W69897880 modified "2023-09-27" @default.
• W69897880 title "Search problems for speech and audio sequences" @default.
• W69897880 cites W114079575 @default.
• W69897880 cites W116133375 @default.
• W69897880 cites W1496038746 @default.
• W69897880 cites W1498269992 @default.
• W69897880 cites W1499399937 @default.
• W69897880 cites W1525128434 @default.
• W69897880 cites W1525353239 @default.
• W69897880 cites W1543564942 @default.
• W69897880 cites W1557074680 @default.
• W69897880 cites W1567365482 @default.
• W69897880 cites W1582482241 @default.
• W69897880 cites W1593045043 @default.
• W69897880 cites W1598908599 @default.
• W69897880 cites W1710422233 @default.
• W69897880 cites W1828401780 @default.
• W69897880 cites W1861596447 @default.
• W69897880 cites W1880262756 @default.
• W69897880 cites W190299453 @default.
• W69897880 cites W1964917299 @default.
• W69897880 cites W1972770363 @default.
• W69897880 cites W1978394996 @default.
• W69897880 cites W1991821078 @default.
• W69897880 cites W1998224037 @default.
• W69897880 cites W2007760849 @default.
• W69897880 cites W2014235936 @default.
• W69897880 cites W2023854218 @default.
• W69897880 cites W2026609075 @default.
• W69897880 cites W2030839740 @default.
• W69897880 cites W2037965136 @default.
• W69897880 cites W2046932483 @default.
• W69897880 cites W2047411082 @default.
• W69897880 cites W2047632477 @default.
• W69897880 cites W2048892273 @default.
• W69897880 cites W2053569739 @default.
• W69897880 cites W2064988570 @default.
• W69897880 cites W2070830131 @default.
• W69897880 cites W2074932712 @default.
• W69897880 cites W2076694837 @default.
• W69897880 cites W2085904853 @default.
• W69897880 cites W2090957374 @default.
• W69897880 cites W2095345875 @default.
• W69897880 cites W2095955955 @default.
• W69897880 cites W2098162425 @default.
• W69897880 cites W2098741345 @default.
• W69897880 cites W2100294832 @default.
• W69897880 cites W2103914106 @default.
• W69897880 cites W2104160358 @default.
• W69897880 cites W2105778889 @default.
• W69897880 cites W2106918957 @default.
• W69897880 cites W2107743791 @default.
• W69897880 cites W2111732304 @default.
• W69897880 cites W2118315228 @default.
• W69897880 cites W2119425792 @default.
• W69897880 cites W2119821739 @default.
• W69897880 cites W2124585778 @default.
• W69897880 cites W2125529971 @default.
• W69897880 cites W2126410803 @default.
• W69897880 cites W2130865646 @default.
• W69897880 cites W2132714218 @default.
• W69897880 cites W2132870739 @default.
• W69897880 cites W2134636339 @default.
• W69897880 cites W2135909747 @default.
• W69897880 cites W2137130182 @default.
• W69897880 cites W2145027719 @default.
• W69897880 cites W2148603752 @default.
• W69897880 cites W2149041454 @default.
• W69897880 cites W2153635508 @default.
• W69897880 cites W2154104338 @default.
• W69897880 cites W2159083595 @default.
• W69897880 cites W2160726788 @default.
• W69897880 cites W2161564256 @default.
• W69897880 cites W2161793958 @default.
• W69897880 cites W2164232160 @default.
• W69897880 cites W2165320163 @default.
• W69897880 cites W2183390198 @default.
• W69897880 cites W2200019713 @default.
• W69897880 cites W2334889010 @default.
• W69897880 cites W2407889405 @default.
• W69897880 cites W2610179052 @default.
• W69897880 cites W3021908862 @default.
• W69897880 cites W3037715718 @default.
• W69897880 cites W605575788 @default.
• W69897880 cites W95202560 @default.
• W69897880 cites W1573672302 @default.
• W69897880 hasPublicationYear "2009" @default.
• W69897880 type Work @default.
• W69897880 sameAs 69897880 @default.
• W69897880 citedByCount "2" @default.
• W69897880 countsByYear W698978802016 @default.
• W69897880 crossrefType "journal-article" @default.
• W69897880 hasAuthorship W69897880A5058585526 @default.
• W69897880 hasAuthorship W69897880A5058849006 @default.
• W69897880 hasConcept C112505250 @default.

• next