Analysis of Emotional Speech—A Review

Abstract

Speech carries information not only about the lexical content, but also about the age, gender, signature and emotional state of the speaker. Speech in different emotional states is accompanied by distinct changes in the production mechanism. In this chapter, we present a review of analysis methods used for emotional speech. In particular, we focus on the issues in data collection, feature representations and development of automatic emotion recognition systems. The significance of the excitation source component of speech production in emotional states is examined in detail. The derived excitation source features are shown to carry the emotion correlates. IntroductionHumans have evolved various forms of communication like facial expressions, gestures, body postures, speech, etc. The form of communication depends on the context of interaction, and is often accompanied by various physiological reactions such as changes in the heart rate, skin resistance, temperature, muscle activity and blood pressure. All forms of human communication carry information at two levels, the message and the underlying emotional state.Emotions are essential part of real life communication among human beings. Various descriptions of the term emotion are studied in [21,22,60,88,92,98,100]. Some of the descriptions are: (a) "Emotions are underlying states which are evolved and adaptive. Emotion expressions are produced by the communicative value of underlying states" [22].

Speaker Discrimination Using Long-Term Spectrum of Speech

“…In future work, the long-term speech spectrum and extracted spectral parameters will be tested for their robustness to various factors affecting speech, such as emotions [7], physical fatigue [12], vocal effort [9,28], and others [4]. Furthermore, it will be useful to also investigate the influence of adverse acoustic conditions, especially non-stationary noises [29] due to their indirect influence on speech production.…”

“…The reference values were obtained and stored in system database during training. Due to the very unbalanced numerical values of both parameter types (e.g., in the lowest subband E>10 7 and K<-1), each individual difference (x R ─ x) 2 is scaled by the denominator (x R ) 2 before summing in Equation (8). In the case of the simplest recognition based on one parameter extracted from one subband, Equation (8) can be reduced to the form…”

A Quantitative Comparison of Epoch Extraction Algorithms for Telephone Speech

“…Identification of epoch locations plays a crucial role in many speech processing applications such as speech modification [1], excitation source modeling [2], inverse filtering [3,4], joint optimization in concatenative speech synthesis [5], speech pathology [6,7], etc. Apart from above applications, the high SNR property of the GCI was used in applications like glottal activity detection [8], pitch tracking [9,10], formant frequencies [11], analysis and detection of phonation types [12,13] and emotions [14,15], speaker recognition [16], speech enhancement [8], multi-speaker separation, identification of number of speakers from multi-speakers data [17] etc. Due to wider range of applications, GCI detection has received a considerable amount of research attention.…”

Speech Emotion Recognition Considering Local Dynamic Features

“…Besides, the prosodic features conveying significant emotional information are utilized and analyzed in many previous studies [2], [8]. Pitch, as one of the prosodic features, has been found discriminative across different emotions, to some extent.…”