Towards expressive musical robots: a cross-modal framework for emotional gesture, voice and music

EURASIP Journal on Audio, Speech, and Music Processing

Table 1 DESIRE parameters and associated emotional features for modalities of voice, gesture and music

		Modality mappings to relevant emotional features
Parameter	Description	Voice	Gesture	Music
Speed	slow vs. fast	speech rate [20], pauses [18]	velocity [35], animation [36], quantity of motion [28]	tempo[24, 26]
Intensity	gradual vs. abrupt	voice onset rapidity [18], articulation [20]	acceleration [35], power [37]	note attack [24], articulation [26]
Regularity	smooth vs. rough	jitter [18], voice quality [18, 20]	directness [35], phase shift [38, 39], fluidity [27]	microstructural irregularity [26], timbral roughness [24]
Extent	small vs. large	pitch range [20], loudness [18]	spatial expansiveness [36, 37], contraction index [35]	volume[24, 26]