Sparse Autoencoder with Attention Mechanism for Speech Emotion Recognition
Authors:
- 1 March 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 521, 146-149
Abstract
There has been a lot of previous works on speech emotion with machine learning method. However, most of them rely on the effectiveness of labelled speech data. In this paper, we propose a novel algorithm which combines both sparse autoencoder and attention mechanism. The aim is to benefit from labeled and unlabeled data with autoencoder, and to apply attention mechanism to focus on speech frames which have strong emotional information. We can also ignore other speech frames which do not carry emotional content. The proposed algorithm is evaluated on three public databases with cross-language system. Experimental results show that the proposed algorithm provide significantly higher accurate predictions compare to existing speech emotion recognition algorithms.Keywords
This publication has 12 references indexed in Scilit:
- Speech Emotion Recognition Using Deep Convolutional Neural Network and Discriminant Temporal Pyramid MatchingIEEE Transactions on Multimedia, 2017
- Semisupervised Autoencoders for Speech Emotion RecognitionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2017
- Emotion Classification Using Segmentation of Vowel-Like and Non-Vowel-Like RegionsIEEE Transactions on Affective Computing, 2017
- Automatic speech emotion recognition using recurrent neural networks with local attention2017
- Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network2016
- Deep learningNature, 2015
- Speech Emotion Recognition Using Fourier ParametersIEEE Transactions on Affective Computing, 2015
- Convolutional Neural Networks for Speech RecognitionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- Survey on speech emotion recognition: Features, classification schemes, and databasesPattern Recognition, 2011
- IEMOCAP: interactive emotional dyadic motion capture databaseLanguage Resources and Evaluation, 2008