A multi-dilated convolution network for speech emotion recognition

Abstract Speech emotion recognition (SER) is an important application in Affective Computing and Artificial Intelligence. Recently, there has been a significant interest in Deep Neural Networks using speech spectrograms. As the two-dimensional representation of the spectrogram includes more speech c...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Samaneh Madanian, Olayinka Adeleye, John Michael Templeton, Talen Chen, Christian Poellabauer, Enshi Zhang, Sandra L. Schneider
Format:	Artigo
Jezik:	Inglês
Izdano:	Nature Portfolio 2025-03-01
Serija:	Scientific Reports
Teme:	Speech emotion recognition Deep learning Convolution neural network Loss layer Spectrogram Emotion recognition
Online dostop:	https://doi.org/10.1038/s41598-025-92640-2
Oznake:	Označite Brez oznak, prvi označite!