Skip to main content


Fig. 1 | EURASIP Journal on Audio, Speech, and Music Processing

Fig. 1

From: Articulation constrained learning with application to speech emotion recognition

Fig. 1

Relationship between angry (left panel) and sad (right panel) emotions, acoustic characteristics, and articulatory information for an utterance “compare me to” by a male speaker. (Top row) Spectrogram and formant tracks, (middle row) position of the jaw along Y-axis, and (bottom row) position of the lip along Y-axis. Note the differences in articulatory position and frequency response for vowels /AE/ and /IY/ of words “compare” and “me”, respectively. Negative axis corresponds to downward movement along the Y-axis

Back to article page