| US 7,606,701 B2 | ||
| Method and apparatus for determining emotional arousal by speech analysis | ||
| Yoav Degani, Emek Hefer (Israel); and Yishai Zamir, Givataim (Israel) | ||
| Assigned to VoiceSense, Ltd., Kefar Sava (Israel) | ||
| Appl. No. 10/485,254 PCT Filed Aug. 07, 2002, PCT No. PCT/IL02/00648 § 371(c)(1), (2), (4) Date Mar. 25, 2004, PCT Pub. No. WO03/015079, PCT Pub. Date Feb. 20, 2003. |
||
| Claims priority of application No. 144818 (IL), filed on Aug. 09, 2001. | ||
| Prior Publication US 2004/0249634 A1, Dec. 09, 2004 | ||
| Int. Cl. G10L 11/04 (2006.01); G10L 19/00 (2006.01); G10L 21/00 (2006.01) | ||
| U.S. Cl. 704—207 [704/217; 704/270] | 20 Claims |
| 1. A method for determining emotional arousal of a subject by speech analysis, comprising the steps of:
obtaining a speech sample;
pre-processing the speech sample into silent and active speech segments and dividing the active speech segments into strings
of equal length blocks; said blocks having primary speech parameters including pitch and amplitude parameters;
deriving a plurality of selected secondary speech parameters indicative of characteristics of equal-pitch, rising-pitch and
falling-pitch trends in said strings of blocks;
comparing said secondary speech parameters with predefined, subject independent values representing non-emotional speech to
generate a processing result indicative of emotional arousal, and outputting said generated processed result to an output
device, wherein said secondary speech parameters comprise:
(a) average length of short silences and number of short silences per unit of time;
(b) average length of equal pitch segments and number of equal pitch segments per unit of time;
(c) rising pitch segments length average and number of rising pitch segments per unit of time and falling pitch segments length
average and number of falling pitch segments per unit of time; and
(d) average amplitude dispersion within equal pitch segments of speech.
|