Speech Emotion Recognition with Local-Global Aware Deep Representation Learning
Authors:
- 1 May 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7174-7178
Abstract
Convolutional neural network (CNN) based deep representation learning methods for speech emotion recognition (SER) have demonstrated great success. The basic design of CNN restricts the ability to model only local information well. Capsule network (CapsNet) can overcome the shortages of CNNs to capture the shallow global features from the spectrogram, although CapsNet cannot learn the local and deep global information. In this paper, we propose a local-global aware deep representation learning system that mainly includes two modules. One module contains a multi-scale CNN, time- frequency CNN (TFCNN) to learn the local representation. In the other module, we introduce a structure with dense connections of multiple blocks to learn shallow and deep global information. Every block in this structure is a complete CapsNet improved by a new routing algorithm. The local and global representations are fed to the classifier and achieve an absolute increase of at least 4.25% than benchmarks on IEMOCAP.Keywords
This publication has 10 references indexed in Scilit:
- Cross-Domain Sentiment Classification by Capsule Network With Semantic RulesIEEE Access, 2018
- An Attention Pooling Based Representation Learning Method for Speech Emotion Recognition2018
- 3-D Convolutional Recurrent Neural Networks With Attention Model for Speech Emotion RecognitionIEEE Signal Processing Letters, 2018
- A Feature Fusion Method Based on Extreme Learning Machine for Speech Emotion Recognition2018
- Efficient Emotion Recognition from Speech Using Deep Learning on Spectrograms2017
- Speech emotion recognition using DWT2015
- Emotion recognition from speech using global and local prosodic featuresInternational Journal of Speech Technology, 2012
- Speech emotion recognition approaches in human computer interactionTelecommunication Systems, 2011
- A dimensional approach to emotion recognition of speech from movies2009
- IEMOCAP: interactive emotional dyadic motion capture databaseLanguage Resources and Evaluation, 2008