Survey on speech emotion recognition: Features, classification schemes, and databases

An efficient solution to the fundamental problem of estimating the time-varying amplitude envelope and instantaneous frequency of a real-valued signal that has both an AM and FM structure is provided. Nonlinear combinations of instantaneous signal outputs from the energy operator are used to separate its output energy product into its AM and FM components. The theoretical analysis is done first for continuous-time signals. Then several efficient algorithms are developed and compared for estimating the amplitude envelope and instantaneous frequency of discrete-time AM-FM signals. These energy separation algorithms are used to search for modulations in speech resonances, which are modeled using AM-FM signals to account for time-varying amplitude envelopes and instantaneous frequencies. The experimental results provide evidence that bandpass-filtered speech signals around speech formants contain amplitude and frequency modulations within a pitch period. >

Energy separation in signal modulations with application to speech analysis

It is shown that the nonlinear energy-tracking signal operator Psi (x)=(dx/dt)/sup 2/-xd/sup 2/x/dt/sup 2/ and its discrete-time counterpart can estimate the AM and FM modulating signals. Specifically, Psi can approximately estimate the amplitude envelope of AM signals and the instantaneous frequency of FM signals. Bounds are derived for the approximation errors, which are negligible under general realistic conditions. These results, coupled with the simplicity of Psi , establish the usefulness of the energy operator for AM and FM signal demodulation. These ideas are then extended to a more general class of signals that are sine waves with a time-varying amplitude and frequency and thus contain both an AM and an FM component; for such signals it is shown that Psi can approximately track the product of their amplitude envelope and their instantaneous frequency. The theoretical analysis is done for both continuous- and discrete-time signals. >

On amplitude and frequency demodulation using energy operators

A compact and efficient algorithm for digital envelope detection in white light interferograms is derived from a well-known phase-shifting algorithm. The performance of the new algorithm is compared with that of other schemes currently used. Principal criteria considered are computational efficiency and accuracy in the presence of miscalibration. The new algorithm is shown to be near optimal in terms of computational efficiency and can be represented as a second-order nonlinear filter. In combination with a carefully designed peak detection method the algorithm exhibits exceptionally good performance on simulated interferograms.

https://nontrivialzeros.net/KGL_Papers/23_Neat_Algorithm_JOSAA96.pdf

Efficient nonlinear algorithm for envelope detection in white light interferometry

Studies have shown that variability introduced by stress or emotion can severely reduce speech recognition accuracy. Techniques for detecting or assessing the presence of stress could help improve the robustness of speech recognition systems. Although some acoustic variables derived from linear speech production theory have been investigated as indicators of stress, they are not always consistent. Three new features derived from the nonlinear Teager (1980) energy operator (TEO) are investigated for stress classification. It is believed that the TEO based features are better able to reflect the nonlinear airflow structure of speech production under adverse stressful conditions. The features proposed include TEO-decomposed FM variation (TEO-FM-Var), normalized TEO autocorrelation envelope area (TEO-Auto-Env), and critical band based TEO autocorrelation envelope area (TEO-CB-Auto-Env). The proposed features are evaluated for the task of stress classification using simulated and actual stressed speech and it is shown that the TEO-CB-Auto-Env feature outperforms traditional pitch and mel-frequency cepstrum coefficients (MFCC) substantially. Performance for TEO based features are maintained in both text-dependent and text-independent models, while performance of traditional features degrades in text-independent models. Overall neutral versus stress classification rates are also shown to be more consistent across different stress styles.

/pdf/nonlinear-feature-based-classification-of-speech-under-22dyi3w58d.pdf

Nonlinear feature based classification of speech under stress

A simple algorithm is derived that permits on-the-fly calculation of the energy required to generate, in a certain sense, a signal. The results of applying this algorithm to a number of well-known signals are shown. Some of the invariance and noise properties of the algorithm are derived and verified by simulation. The implementation of the algorithm and its application to speech processing are briefly discussed. >

J.F. Kaiser

Papers

On a simple algorithm to calculate the 'energy' of a signal