Multimodal emotion recognition with evolutionary computation for human-robot interaction

作者：

Highlights：

• A multimodal emotion recognition system was developed with HMMs, ANNs, and PCA.

• Text stimuli was designed to create an emotional speech database of Mexican users.

• Genetic algorithms improved the performance of HMMs and ANNs for emotion recognition.

• A dialogue system was developed for interaction with a humanoid robot.

• Live test with different users showed a multimodal emotion recognition rate of 97%.

摘要

Highlights•A multimodal emotion recognition system was developed with HMMs, ANNs, and PCA.•Text stimuli was designed to create an emotional speech database of Mexican users.•Genetic algorithms improved the performance of HMMs and ANNs for emotion recognition.•A dialogue system was developed for interaction with a humanoid robot.•Live test with different users showed a multimodal emotion recognition rate of 97%.

论文关键词：Emotion recognition,Principal Component Analysis,Hidden Markov Models,Genetic Algorithms,Artificial Neural Networks,Finite state machines

论文评审过程：Received 4 December 2015, Revised 12 August 2016, Accepted 13 August 2016, Available online 3 September 2016, Version of Record 9 September 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.08.047