Black-box adversarial attacks through speech distortion for speech emotion recognition

Abstract Speech emotion recognition is a key branch of affective computing. Nowadays, it is common to detect emotional diseases through speech emotion recognition. Various detection methods of emotion recognition, such as LTSM, GCN, and CNN, show excellent performance. However, due to the robustness...

Descrizione completa

Dettagli Bibliografici

Autori principali:	Jinxing Gao, Diqun Yan, Mingyu Dong
Natura:	Artigo
Lingua:	Inglês
Pubblicazione:	SpringerOpen 2022-08-01
Serie:	EURASIP Journal on Audio, Speech, and Music Processing
Soggetti:	Convolutional Neural Network Robustness Speech emotion recognition Adversarial attack Adversarial training
Accesso online:	https://doi.org/10.1186/s13636-022-00254-7
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!