Nonlinear feature based classification of speech under stress

By Guojun Zhou, John H. L. Hansen, James F. Kaiser. IEEE Transactions on Speech and Audio Processing, 2001

455 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/e3d0fec996571f62849e09d5196fe3d3e3e06487

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Experimental and Cognitive Psychology

In Signal Processing

Citations in the corpus

Review on Psychological Stress Detection Using Biosignals (2019, methodology): “…Accu- racy achieved Womack and Hansen (1996) [230] 11 subjects men 22-76 simulated/actual stress speech Speech (MFCC, for- mants, etc) HMM 91.00% Zhou et al (2001) [81] 16 subjects 3/13 22-76 simulated/actual stress speech Speech (TEO-CB- Auto-Env) HMM 92.90% Kim et al. (2004) [231]…”
EMOTION RECOGNITION BY SPEECH SIGNAL (2003, methodology): “Following the experimental setup of text-independent stress style classification in [ 5 ], we chose 3 stressed styles (angry, Lombard and loud) and a neutral style.”
Speech Recognition Using Deep Neural Networks: A Systematic Review (2019, background): “Automatic health recognition can be used in intelligent health care systems [17], [18].”
Objective measures, sensors and computational techniques for stress recognition and classification: A survey (2012, methodology): “In stress research, HMMs have been mainly used in recogising stressed speech [106,107,110,123].”
Survey on speech emotion recognition: Features, classification schemes, and databases (2011, background): “It is verified that the TEO of multi-frequency signal does not only reflects individual frequency components but also interaction between them [145].”
Accelerating Mobile Audio Sensing Algorithms through On-Chip GPU Offloading (2017, methodology): “Application Purpose Main Features Inference Model Frame Window Emotion Recognition∗ [52] emotion recognition PLP∗ [32] 14 Gaussian Mixture Models∗ [18] 30ms 5s Speaker Identification∗ [52] speaker identification PLP∗ 23 Gaussian Mixture Models∗ 30ms 5s Keyword Spotting∗ [22] hotphrase recognition Fi”
Automatic speech emotion recognition using modulation spectral features (2011, background): “TEO extracts useful information about the nonlinear airflow structure of speech production (Zhou et al., 2001).”
A Comprehensive Review of Speech Emotion Recognition Systems (2021, unknown): “Normalized TEO auto-correlation envelope area, TEO-decomposed frequency modulation variation, and critical band-based TEO auto-correlation envelope area are the three new TEO-based features introduced by [44].”
Emotional speech recognition: Resources, features, and methods (2006, methodology): “The polynomial coefficients, which describe the TEO autocorrelation envelope area, can be used as features for classifying the speech into emotional states (Zhou et al., 2001).”
A review of depression and suicide risk assessment using speech analysis (2015, background): “, 1993) one application being detection of speech under stress (Zhou et al., 2001).”
Speech Emotion Recognition Using Fourier Parameters (2015, background): “There are also other TEObased features proposed for detecting neutral versus stressed speech [38].”
Emotion recognition from speech: a review (2012, background): “The Teager energy values and MFCC features are combined in Zhou et al. (2001), for classifying neutral and stressed speech.”