Convolutional-Recurrent Neural Networks With Multiple Attention Mechanisms for Speech Emotion Recognition

Speech emotion recognition (SER) aims to endow machines with the intelligence in perceiving latent affective components from speech. However, the existing works on deep-learning-based SER make it difficult to jointly consider time-frequency and sequential information in speech due to their structure...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on cognitive and developmental systems 2022-12, Vol.14 (4), p.1564-1573
Hauptverfasser:	Jiang, Pengxu, Xu, Xinzhou, Tao, Huawei, Zhao, Li, Zou, Cairong
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Convolutional neural networks Convolutional neural networks (CNNs) Data mining Emotion recognition Emotions Feature extraction Long short term memory long short-term memory (LSTM) Machine learning Modules multiple attention mechanisms Neural networks Recurrent neural networks speech emotion recognition (SER) Speech recognition Time-frequency analysis
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!