摘要 |
PROBLEM TO BE SOLVED: To enable a person to easily estimate audience status, without having to observe the audience status. SOLUTION: An input section 20 generates a speech signal SA corresponding to a speech from an audience. A feature quantity detection section 30 (80) detects information, regarding, for example loudness, periodicity, and frequency components of the speech from the audience, based on the speech signal SA. An estimation section 40 (90) estimates the audience state, based on the detection result. An output section 50 outputs the estimation result of the audience state. The audience state can be estimated from the speech signal SA, without having to observe the audience state. COPYRIGHT: (C)2007,JPO&INPIT
|