Domain adversarial learning for emotion recognition

10/24/2019
by   Zheng Lian, et al.
0

In practical applications for emotion recognition, users do not always exist in the training corpus. The mismatch between training speakers and testing speakers affects the performance of the trained model. To deal with this problem, we need our model to focus on emotion-related information, while ignoring the difference between speaker identities. In this paper, we look into the use of the domain adversarial neural network (DANN) to extract a common representation between different speakers. The primary task is to predict emotion labels. The secondary task is to learn a common representation where speaker identities can not be distinguished. By using the gradient reversal layer, the gradients coming from the secondary task are used to bring the representations for different speakers closer. To verify the effectiveness of the proposed method, we conduct experiments on the IEMOCAP database. Experimental results demonstrate that the proposed framework shows an absolute improvement of 3.48

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/24/2019

Conversational Emotion Analysis via Attention Mechanisms

Different from the emotion recognition in individual utterances, we prop...
research
04/20/2018

Domain Adversarial for Acoustic Emotion Recognition

The performance of speech emotion recognition is affected by the differe...
research
03/22/2019

Towards adversarial learning of speaker-invariant representation for speech emotion recognition

Speech emotion recognition (SER) has attracted great attention in recent...
research
09/05/2023

Personalized Adaptation with Pre-trained Speech Encoders for Continuous Emotion Recognition

There are individual differences in expressive behaviors driven by cultu...
research
10/24/2019

Unsupervised Representation Learning with Future Observation Prediction for Speech Emotion Recognition

Prior works on speech emotion recognition utilize various unsupervised l...
research
10/29/2019

Privacy Enhanced Multimodal Neural Representations for Emotion Recognition

Many mobile applications and virtual conversational agents now aim to re...
research
03/26/2014

Constrained speaker linking

In this paper we study speaker linking (a.k.a. partitioning) given const...

Please sign up or login with your details

Forgot password? Click here to reset