EURASIP Journal on Audio, Speech, and Music Processing

Table 1 Recall values (%) for categorical recognition on USC IEMOCAP

From: Within and cross-corpus speech emotion recognition using latent topic model-based features

Metric	IS09	VQ	LDA	sLDA	RSM	sRSM
Neu	53.62	39.64	51.70	52.46	49.88	56.38
Sad	62.45	71.31	66.79	67.34	74.72	70.39
Hap	47.00	54.10	50.37	51.53	54.77	54.76
Ang	57.57	49.95	52.04	52.95	52.31	54.58
WA	54.17	52.18	54.33	55.20	56.68	58.29
UA	55.14	51.94	55.22 ^†	56.07 ^†	57.92 ^∗†	59.03 ^∗†

Symbols ∗ and † indicate statistical significance over IS09 and VQ, respectively.

Back to article page