Revisiting Hidden Markov Models for Speech Emotion Recognition
Refereed conference paper presented and published in conference proceedings

Times Cited
Altmetrics Information

Other information
AbstractHidden Markov models (HMMs) have a long tradition in automatic speech recognition (ASR) due to their capability of capturing temporal dynamic characteristics of speech. For emotion recognition from speech, three HMM based architectures are investigated and com-pared throughout the current paper, namely, the Gaussian mixture model based HMMs (GMM-HMMs), the subspace based Gaussian mixture model based HMMs (SGMM-HMMs) and the hybrid deep neural network HMMs (DNN-HMMs). Extensive emotion recognition experiments are carried out on these three architectures on the CASIA corpus, the Emo-DB corpus and the IEMOCAP database, respectively, and results are compared with those of state-of-the-art approaches. These HMM based architectures prove capable of constituting an effective model for speech emotion recognition. Also, the modeling accuracy is further enhanced by incorporating various advanced techniques from the ASR area. In particular, among all of the architectures, the SGMM-HMMs achieve the best performance in most of the experiments.
Acceptance Date02/02/2019
All Author(s) ListShuiyang MAO, Dehua TAO, Guangyan ZHANG, P.C. CHING, Tan LEE
Name of Conference44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Start Date of Conference12/05/2019
End Date of Conference17/05/2019
Place of ConferenceBrighton
Country/Region of ConferenceGreat Britain
Proceedings TitleProceedings ICASSP 2019
Place of PublicationUSA
Pages6715 - 6719
LanguagesEnglish-United Kingdom
KeywordsSpeech emotion recognition, hidden Markov models, subspace based GMM, hybrid DNN-HMM

Last updated on 2020-23-11 at 01:59