What question did this study set out to answer?

To improve speech emotion classification by combining statistical and temporal features.

March 21, 2005

Speech emotion classification with the combination of statistic features and temporal features

Puntos clave

To improve speech emotion classification by combining statistical and temporal features.
Statistical features modeled using Gaussian Mixture Model (GMM).
Temporal features modeled with Hidden Markov Model (HMM).
Classification performed using a weighted Bayesian classifier and Multi-Layer Perceptron (MLP).
The combined feature approach significantly improved classification accuracy.
Statistical and temporal features compensated each other effectively in the classification.

Resumen

For classifying speech emotion, most previous systems used either statistical features or temporal features exclusively. However, these two distinct feature representations appear to be concerned with different aspects of emotion, and should be combined in the task. This work proposes a classification scheme that enables the combination of them both. In the scheme, GMM and HMM are first performed to model the statistical features and temporal features respectively. Then the GMM likelihoods and HMM likelihoods are used as features in a further procedure. Finally, a weighted Bayesian classifier and MLP are applied to accomplish the classification. Experiments on a Chinese speech corpus have demonstrated that the scheme could improve the classification accuracy greatly. More detailed analysis indicated that these two feature representations could compensate each other efficiently in the classification.

Preguntar a la IA

Me gusta

Guardar