Analysis of excitation source features of speech for emotion recognition

Kadiri, Sudarsana Reddy; Gangamohan, P.; Gangashetty, Suryakanth V.; Yegnanarayana, B.

doi:10.21437/interspeech.2015-329

Cited by 27 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These features were shown to be useful for discriminating phonation types in speech and singing [13], [41], [42]. SoE was shown to be proportional to the rate of glottal closure, the EoE feature was shown to capture the vocal effort, and the loudness measure was shown to capture the abruptness of the glottal closure [43], [44]. The energy of the ZFF signal at glottal closure is also used as a feature, it was shown to capture low frequency energy [13].…”

Section: ) Zero Frequency Filtering (Zff)mentioning

confidence: 99%

Classification of Phonation Modes in Classical Singing Using Modulation Power Spectral Features

et al. 2023

Self Cite

View full text Add to dashboard Cite

In singing, the perceptual term "voice quality" is used to describe expressed emotions and singing styles. In voice physiology research, specific voice qualities are discussed by the term phonation modes and are related directly to the voicing produced by the vocal folds. The control and awareness of phonation modes is vital for professional singers to maintain a healthy voice. Most studies on phonation modes have investigated speech and have used glottal inverse filtering to compute features from an estimated excitation signal. The performance of this method is reported to decrease at high pitches, which limits its usability for the singing voice. To overcome this, this study proposes to use features derived from the modulation power spectrum for phonation mode classification in the singing voice. The exploration of the modulation power spectrum is motivated by the fact that, in singing, temporal modulations (known as vocal vibrato) and spectral modulations hold information of the vocal fold tension. Since there exists no large publicly available dataset of phonation modes in singing, we created a new dataset consisting of six female and four male classical singers, who sang five vowels at different pitches in three phonation modes (breathy, modal, and pressed). Experimental results with a support vector machine classifier reveal that the proposed features show better classification performance compared to state-of-the-art reference features. The performance for the current dataset is at least 10% higher compared to the performance of the reference features (such as glottal source features and MFCCs) in the case of target labels and around 6% higher in the case of perceptually assessed labels.INDEX TERMS Modulation power spectrum, phonation modes, singing voice analysis, voice qualities.

show abstract

Section: ) Zero Frequency Filtering (Zff)mentioning

confidence: 99%

Classification of Phonation Modes in Classical Singing Using Modulation Power Spectral Features

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…In protocol 1, where the number of output classes M=2, the cross-entropy was calculated by using (12). Similarly, in the 2 nd protocol, as the number of output classes is three, the categorical cross-entropy was calculated by (13).…”

Section: H Optimization Algorithm and Cost Functionmentioning

confidence: 99%

“…To recognize human emotion, many scholars used various types of raw signals [6]. Many used EEG signals [2], [7]- [9] and facial expressions [10], [11]; and few used gesture, speech signals [12], autonomous nervous signals [13]. Subjects need to express emotion explicitly when facial expressions and speech signals are being used.…”

Section: Introductionmentioning

confidence: 99%

EEG Channel Correlation Based Model for Emotion Recognition

Islam

Rahman³

et al. 2021

Computers in Biology and Medicine

View full text Add to dashboard Cite

“…Knowledge of GCIs help in several speech processing situations such as the detection of glottal activity region [33], pitch extraction [49], estimation of formant frequencies [15], characteristics of loudness [38], analysis of non-verbal sounds (such as laughter [31] and shout [30]), pitch extraction from multi-speaker data [50] and voice source analysis [47,2,3,9]. Also, GCI-based analysis of speech can be used in several speech processing applications such as concatenative speech synthesis [42], parametric speech synthesis [1], analysis and detection of pathological speech [28,39], analysis and detection of phonation types [22,21] and emotions [13,18], time delay estimation [51], determination of number of speakers from mixed signals [43], multi-speaker separation [7] and prosody modification [37]. Due to wider range of applications, detection of GCIs directly from the speech signal has received a considerable amount of research attention.…”

Section: Introductionmentioning

confidence: 99%