Speech emotion recognition by using complex MFCC and deep sequential model

Suprava Patnaik

doi:10.1007/s11042-022-13725-y

Speech emotion recognition by using complex MFCC and deep sequential model

2022-09-12

26

PRE

AI

S

Suprava Patnaik *

DOI：10.1007/s11042-022-13725-y

原文链接

原文求助

摘要

En 中文

Speech Emotion Recognition (SER) is one of the front-line research areas. For a machine, inferring SER is difficult because emotions are subjective and annotation is challenging. Nevertheless, researchers feel that SER is possible because speech is quasi-stationery and emotions are declarative finite states. This paper is about emotion classification by using Complex Mel Frequency Cepstral Coefficients (c-MFCC) as the representative trait and a deep sequential model as a classifier. The experimental setup is speaker independent and accommodates marginal variations in the underlying phonemes. Testing for this work has been carried out on RAVDESS and TESS databases. Conceptually, the proposed model is erogenous towards prosody observance. The main contributions of this work are of two-folds. Firstly, introducing conception of c-MFCC and investigating it as a robust cue of emotion and there by leading to significant improvement in accuracy performance. Secondly, establishing correlation between MFCC based accuracy and Russell's emotional circumplex pattern. As per the Russell's 2D emotion circumplex model, emotional signals are combinations of several psychological dimensions though perceived as discrete categories. Results of this work are outcome from a deep sequential LSTM model. Proposed c-MFCC are found to be more robust to handle signal framing, informative in terms of spectral roll off, and therefore put forward as an input to the classifier. For RAVDESS database the best accuracy achieved is 78.8% for fourteen classes, which subsequently improved to 91.6% for gender integrated eight classes and 98.5% for affective separated six classes. Though, the RAVDESS dataset has two analogous sentences revealed results are for the complete dataset and without applying any phonetic separation of the samples. Thus, proposed method appears to be semi-commutative on phonemes. Results obtained from this study are presented and discussed in forms of confusion matrices.

Keyword:

Speech emotion

MFCC

Emotion circumplex

1-D CNN

Speech emotion recognition by using complex MFCC and deep sequential model

摘要

期刊

机构

引用论文