Some articulatory details of emotional speech

Abstract

Differences in speech articulation among four emotion types, neutral, anger, sadness, and happiness are investigated by analyzing tongue tip, jaw, and lip movement data collected from one male and one female speaker of American English. The data were collected using an electromagnetic articulography (EMA) system while subjects produce simulated emotional speech. Pitch, root-mean-square (rms) energy and the first three formants were estimated for vowel segments. For both speakers, angry speech exhibited the largest rms energy and largest articulatory activity in terms of displacement range and movement speed. Happy speech is characterized by largest pitch variability. It has higher rms energy than neutral speech but articulatory activity is rather comparable to, or less than, neutral speech. That is, happy speech is more prominent in voicing activity than in articulation. Sad speech exhibits longest sentence duration and lower rms energy. However, its articulatory activity is no less than neutral speech. Interestingly, for the male speaker, articulation for vowels in sad speech is consistently more peripheral (i.e., more forwarded displacements) when compared to other emotions. However, this does not hold for female subject. These and other results will be discussed in detail with associated acoustics and perceived emotional qualities. [Work supported by NIH.]

Analysis of Emotionally Salient Aspects of Fundamental Frequency for Emotion Detection

“…These emotional databases were chosen to span different emotional categories, speakers, genders, and even languages, with the purpose to include, to some extent, the variability found in the pitch. The first database was collected at the University of Southern California (USC) using an electromagnetic articulography (EMA) system [21]. In this database, which will be referred to here on as EMA, one male and two female subjects (two of them with formal theatrical vocal training) read ten sentences five times portraying the emotions sadness, anger, and happiness, in addition to neutral state.…”

Upgrading the Performance of Speech Emotion Recognition at the Segmental Level

“…Lee et. al., [7] conducted a study of the averaged tongue tip movement velocity for each of four peripheral vowels sounds (/IY/, /AE/, /AA/, /UW/) in American English as a function of four emotions. Results indicated angry speech to be characterized by greater ranges of displacement and velocity, while it was opposite in sad speech.…”

Iterative feature normalization for emotional speech detection

“…Similar to the experimental set up used in our previous work [6], three emotional databases are used: USC-EMA [8], EMO-DB [9], and EPSAT [10]. Table 1 gives details about these corpora.…”