The spontaneous emotional speech database comprising utterances from dialogs among online game players chatting through a voice chat system was examined. The dialogs among online game players were recorded to collect a wide variety of spontaneously expressed emotional speech. The players were 13 university students with experience in the online game and their average playing time per month was 33 hours and the average month of experience was 38 months. Each group member was asked to participate in game events together as a party to keep talking with each other and asked to use a voice chat system and were prohibited from using a text chat function provided by the online game system when they talked with each other. The voice-recording system for Skype, Tapur, recorded the local player's voice and remote player's voices in individual channels of a stereo sound file. The results showed that intensity and similarity of emotion are two of the components of the emotional space perceived by humans when they listen to emotional speech.
|ジャーナル||Acoustical Science and Technology|
|出版ステータス||Published - 2011|
ASJC Scopus subject areas