Selection of Features for Multimodal Vocalic Segments Classification - Publikacja - MOST Wiedzy

Wyszukiwarka

Selection of Features for Multimodal Vocalic Segments Classification

Abstrakt

English speech recognition experiments are presented employing both: audio signal and Facial Motion Capture (FMC) recordings. The principal aim of the study was to evaluate the influence of feature vector dimension reduction for the accuracy of vocalic segments classification employing neural networks. Several parameter reduction strategies were adopted, namely: Extremely Randomized Trees, Principal Component Analysis and Recursive Parameter Elimination. The feature extraction process is explained, applied feature selection methods are presented and obtained results are discussed

Cytowania

0
CrossRef
0
Web of Science
0
Scopus

Szymon Zaporowski, Andrzej Czyżewski. (2019). Selection of Features for Multimodal Vocalic Segments Classification, 490-500. https://doi.org/10.1007/978-3-319-98677-4

Informacje szczegółowe

Kategoria:
Inna publikacyjna praca zbiorowa (w tym materiały konferencyjne)
Typ:
publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)
Tytuł wydania:
Multimedia and Network Information Systems : Proceedings of the 11th International Conference MISSI 2018 strony 490 - 500
Język:
angielski
Rok wydania:
2019
Opis bibliograficzny:
Zaporowski S., Czyżewski A.: Selection of Features for Multimodal Vocalic Segments Classification// Multimedia and Network Information Systems : Proceedings of the 11th International Conference MISSI 2018/ ed. Kazimierz Choroś, Marek Kopel, Elzbieta Kukla, Andrzej Sieminski : Springer, 2019, s.490-500

wyświetlono 3 razy

Publikacje, które mogą cię zainteresować

Meta Tagi