Psychosis speech recognition algorithm based on deep embedded sparse stacked autoencoder and manifold ensemble

Speech feature learning is the core and key of speech recognition method for mental illness. Deep feature learning can automatically extract speech features, but it is limited by the problem of small samples. Traditional feature extraction (original features) can avoid the impact of small samples, b...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Sheng wu yi xue gong cheng xue za zhi Ročník 38; číslo 4; s. 655
Hlavní autoři: Zhang, Yi, Qin, Xiaolin, Lin, Yuan, Li, Yongming, Wang, Pin, Zhang, Zuwei, Li, Xiaofei
Médium: Journal Article
Jazyk:čínština
Vydáno: China 25.08.2021
Témata:
Algorithms
Databases, Factual
Humans
Psychotic Disorders
Speech
Speech Perception
psychosis speech recognition
feature fusion
L1 regularization
embedded hybrid features sparse stacked autoencoder
manifold ensemble learning
ISSN:1001-5515
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Speech feature learning is the core and key of speech recognition method for mental illness. Deep feature learning can automatically extract speech features, but it is limited by the problem of small samples. Traditional feature extraction (original features) can avoid the impact of small samples, but it relies heavily on experience and is poorly adaptive. To solve this problem, this paper proposes a deep embedded hybrid feature sparse stack autoencoder manifold ensemble algorithm. Firstly, based on the prior knowledge, the psychotic speech features are extracted, and the original features are constructed. Secondly, the original features are embedded in the sparse stack autoencoder (deep network), and the output of the hidden layer is filtered to enhance the complementarity between the deep features and the original features. Third, the L1 regularization feature selection mechanism is designed to compress the dimensions of the mixed feature set composed of deep features and original features. Finally, a weigh
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1001-5515
DOI:10.7507/1001-5515.202010050