FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2343348669> ?p ?o ?g. }

• W2343348669 endingPage "1019" @default.
• W2343348669 startingPage "1006" @default.
• W2343348669 abstract "Spectral information represents short-term speech information within a frame of a few tens of milliseconds, while temporal information captures the evolution of speech statistics over consecutive frames. Motivated by the findings that human speech comprehension relies on the integrity of both the spectral content and temporal envelope of speech signal, we study a spectro-temporal transform framework that adapts run-time speech features to minimize the mismatch between run-time and training data, and its implementation that includes cross transform and cascaded transform. A Kullback-Leibler divergence based cost function is proposed to estimate the transform parameters. We conducted experiments on the REVERB Challenge 2014 task, where clean and multi-condition trained acoustic models are tested with real reverberant and noisy speech. We found that temporal information is important for reverberant speech recognition and the simultaneous use of spectral and temporal information for feature adaptation is effective. We also investigate the combination of the cross transform with fMLLR, the combination of batch, utterance and speaker mode adaptation, and multicondition adaptive training using proposed transforms. All experiments consistently report significant word error rate reductions." @default.
• W2343348669 created "2016-06-24" @default.
• W2343348669 creator A5032690182 @default.
• W2343348669 creator A5057945477 @default.
• W2343348669 creator A5061914075 @default.
• W2343348669 creator A5070872826 @default.
• W2343348669 date "2016-06-01" @default.
• W2343348669 modified "2023-10-16" @default.
• W2343348669 title "Feature Adaptation Using Linear Spectro-Temporal Transform for Robust Speech Recognition" @default.
• W2343348669 cites W1599512239 @default.
• W2343348669 cites W1936118753 @default.
• W2343348669 cites W1965213123 @default.
• W2343348669 cites W1965588146 @default.
• W2343348669 cites W1968428168 @default.
• W2343348669 cites W1968939597 @default.
• W2343348669 cites W1971332722 @default.
• W2343348669 cites W1973211667 @default.
• W2343348669 cites W1973669708 @default.
• W2343348669 cites W1989314204 @default.
• W2343348669 cites W1992475611 @default.
• W2343348669 cites W1999686891 @default.
• W2343348669 cites W2002342963 @default.
• W2343348669 cites W2015337779 @default.
• W2343348669 cites W2038507080 @default.
• W2343348669 cites W2038728370 @default.
• W2343348669 cites W2044893557 @default.
• W2343348669 cites W2050693797 @default.
• W2343348669 cites W2051434435 @default.
• W2343348669 cites W2052667477 @default.
• W2343348669 cites W2054139811 @default.
• W2343348669 cites W2054392851 @default.
• W2343348669 cites W2066561607 @default.
• W2343348669 cites W2069631319 @default.
• W2343348669 cites W2073936352 @default.
• W2343348669 cites W2077651652 @default.
• W2343348669 cites W2080400971 @default.
• W2343348669 cites W2081976287 @default.
• W2343348669 cites W2082474452 @default.
• W2343348669 cites W2091828388 @default.
• W2343348669 cites W2100969003 @default.
• W2343348669 cites W2104780554 @default.
• W2343348669 cites W2107102907 @default.
• W2343348669 cites W2107992675 @default.
• W2343348669 cites W2110606453 @default.
• W2343348669 cites W2115515280 @default.
• W2343348669 cites W2117518720 @default.
• W2343348669 cites W2121973264 @default.
• W2343348669 cites W2121981798 @default.
• W2343348669 cites W2127825510 @default.
• W2343348669 cites W2128653836 @default.
• W2343348669 cites W2129967803 @default.
• W2343348669 cites W2136922672 @default.
• W2343348669 cites W2137075158 @default.
• W2343348669 cites W2138534187 @default.
• W2343348669 cites W2140866802 @default.
• W2343348669 cites W2141132023 @default.
• W2343348669 cites W2142352807 @default.
• W2343348669 cites W2146871184 @default.
• W2343348669 cites W2147166770 @default.
• W2343348669 cites W2149175990 @default.
• W2343348669 cites W2151899309 @default.
• W2343348669 cites W2153529069 @default.
• W2343348669 cites W2155445312 @default.
• W2343348669 cites W2158239695 @default.
• W2343348669 cites W2160815625 @default.
• W2343348669 cites W2164356097 @default.
• W2343348669 cites W2164502538 @default.
• W2343348669 cites W2167152389 @default.
• W2343348669 cites W2171972033 @default.
• W2343348669 cites W3147539069 @default.
• W2343348669 doi "https://doi.org/10.1109/taslp.2016.2522646" @default.
• W2343348669 hasPublicationYear "2016" @default.
• W2343348669 type Work @default.
• W2343348669 sameAs 2343348669 @default.
• W2343348669 citedByCount "6" @default.
• W2343348669 countsByYear W23433486692016 @default.
• W2343348669 countsByYear W23433486692017 @default.
• W2343348669 countsByYear W23433486692018 @default.
• W2343348669 countsByYear W23433486692019 @default.
• W2343348669 countsByYear W23433486692022 @default.
• W2343348669 crossrefType "journal-article" @default.
• W2343348669 hasAuthorship W2343348669A5032690182 @default.
• W2343348669 hasAuthorship W2343348669A5057945477 @default.
• W2343348669 hasAuthorship W2343348669A5061914075 @default.
• W2343348669 hasAuthorship W2343348669A5070872826 @default.
• W2343348669 hasBestOaLocation W23433486692 @default.
• W2343348669 hasConcept C120665830 @default.
• W2343348669 hasConcept C121332964 @default.
• W2343348669 hasConcept C138885662 @default.
• W2343348669 hasConcept C139807058 @default.
• W2343348669 hasConcept C153180895 @default.
• W2343348669 hasConcept C154945302 @default.
• W2343348669 hasConcept C207390915 @default.
• W2343348669 hasConcept C2775852435 @default.
• W2343348669 hasConcept C2776401178 @default.
• W2343348669 hasConcept C28490314 @default.
• W2343348669 hasConcept C41008148 @default.
• W2343348669 hasConcept C41895202 @default.

• next