Matches in SemOpenAlex for { <https://semopenalex.org/work/W3118373341> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3118373341 abstract "Formant estimation from vowel segments, is very useful for linguistic purposes. Traditionally, formants are estimated using classical signal processing methods and statistical models. The averaged continuous extraction of formant frequency along the vowel segments is taken as the formant of vowels. New approaches using neural networks to predict vowel formants on an annotated database, where the input is the acoustic features and output is the mean formant frequency value. Recently, the Bilinear Network (BL) and Temporal Attention-Augmented Bilinear Network (TABL) have proven to be very effective on financial time-series analysis task, compared to recurrent networks and convolution networks. Similar to our work, we explored how to extend the structure of BL and learn from TABL to produce better short-term modeling capability for vowel formant estimation. More specifically, we proposed to replace the attention mechanism with sigmoid gate and use a learnable parameter to dynamically integrate the first linear transformation output, thus learning better representation of BL. Experiments on the vowels test set of public VTR corpus showed that our approach significantly surpassed DNN, CNN, BL and achieved slightly better performance than the poweful TABL model in terms of mean absolute error and mean absolute percent error rate on F1, F2, F3 and overall." @default.
- W3118373341 created "2021-01-18" @default.
- W3118373341 creator A5005058788 @default.
- W3118373341 creator A5006684220 @default.
- W3118373341 creator A5025834611 @default.
- W3118373341 creator A5028749549 @default.
- W3118373341 creator A5033115045 @default.
- W3118373341 date "2020-12-04" @default.
- W3118373341 modified "2023-09-27" @default.
- W3118373341 title "Gated Bilinear Networks for Vowel Formant Estimation" @default.
- W3118373341 cites W1968222399 @default.
- W3118373341 cites W1990496939 @default.
- W3118373341 cites W2049419997 @default.
- W3118373341 cites W2057800825 @default.
- W3118373341 cites W2098885262 @default.
- W3118373341 cites W2100974241 @default.
- W3118373341 cites W2104298309 @default.
- W3118373341 cites W2106610722 @default.
- W3118373341 cites W2132181233 @default.
- W3118373341 cites W2161925948 @default.
- W3118373341 cites W2165544306 @default.
- W3118373341 cites W2166764349 @default.
- W3118373341 cites W2509814936 @default.
- W3118373341 cites W2807696699 @default.
- W3118373341 cites W2912019251 @default.
- W3118373341 cites W2963122061 @default.
- W3118373341 cites W3095938191 @default.
- W3118373341 cites W3098080548 @default.
- W3118373341 cites W3105291792 @default.
- W3118373341 doi "https://doi.org/10.1109/ialp51396.2020.9310481" @default.
- W3118373341 hasPublicationYear "2020" @default.
- W3118373341 type Work @default.
- W3118373341 sameAs 3118373341 @default.
- W3118373341 citedByCount "1" @default.
- W3118373341 countsByYear W31183733412023 @default.
- W3118373341 crossrefType "proceedings-article" @default.
- W3118373341 hasAuthorship W3118373341A5005058788 @default.
- W3118373341 hasAuthorship W3118373341A5006684220 @default.
- W3118373341 hasAuthorship W3118373341A5025834611 @default.
- W3118373341 hasAuthorship W3118373341A5028749549 @default.
- W3118373341 hasAuthorship W3118373341A5033115045 @default.
- W3118373341 hasConcept C109786386 @default.
- W3118373341 hasConcept C154945302 @default.
- W3118373341 hasConcept C158215666 @default.
- W3118373341 hasConcept C205203396 @default.
- W3118373341 hasConcept C2776257435 @default.
- W3118373341 hasConcept C2779581591 @default.
- W3118373341 hasConcept C28490314 @default.
- W3118373341 hasConcept C31972630 @default.
- W3118373341 hasConcept C33923547 @default.
- W3118373341 hasConcept C36390408 @default.
- W3118373341 hasConcept C41008148 @default.
- W3118373341 hasConcept C50644808 @default.
- W3118373341 hasConcept C76155785 @default.
- W3118373341 hasConcept C81388566 @default.
- W3118373341 hasConceptScore W3118373341C109786386 @default.
- W3118373341 hasConceptScore W3118373341C154945302 @default.
- W3118373341 hasConceptScore W3118373341C158215666 @default.
- W3118373341 hasConceptScore W3118373341C205203396 @default.
- W3118373341 hasConceptScore W3118373341C2776257435 @default.
- W3118373341 hasConceptScore W3118373341C2779581591 @default.
- W3118373341 hasConceptScore W3118373341C28490314 @default.
- W3118373341 hasConceptScore W3118373341C31972630 @default.
- W3118373341 hasConceptScore W3118373341C33923547 @default.
- W3118373341 hasConceptScore W3118373341C36390408 @default.
- W3118373341 hasConceptScore W3118373341C41008148 @default.
- W3118373341 hasConceptScore W3118373341C50644808 @default.
- W3118373341 hasConceptScore W3118373341C76155785 @default.
- W3118373341 hasConceptScore W3118373341C81388566 @default.
- W3118373341 hasFunder F4320325046 @default.
- W3118373341 hasFunder F4320335787 @default.
- W3118373341 hasLocation W31183733411 @default.
- W3118373341 hasOpenAccess W3118373341 @default.
- W3118373341 hasPrimaryLocation W31183733411 @default.
- W3118373341 hasRelatedWork W1486821748 @default.
- W3118373341 hasRelatedWork W1582197958 @default.
- W3118373341 hasRelatedWork W1655196610 @default.
- W3118373341 hasRelatedWork W2002094307 @default.
- W3118373341 hasRelatedWork W2029024405 @default.
- W3118373341 hasRelatedWork W2114306283 @default.
- W3118373341 hasRelatedWork W2991474544 @default.
- W3118373341 hasRelatedWork W3118373341 @default.
- W3118373341 hasRelatedWork W3163927590 @default.
- W3118373341 hasRelatedWork W2114876233 @default.
- W3118373341 isParatext "false" @default.
- W3118373341 isRetracted "false" @default.
- W3118373341 magId "3118373341" @default.
- W3118373341 workType "article" @default.