Sound Scene Database in Real Acoustical Environments, Proc. First International Workshop on East-Asian Language Resource and Evaluation
Satoshi Nakamura, Kazuo Hiyane, Futoshi Asano, Takashi Endo · Institutional Repositories DataBase (IRDB) · 1998
This paper describes a sound scene database for studies such as sound source localization, sound retrieval, sound recognition and speech recognition in real acoustical environments. Many speech databases have been released for speech recognition. However, only a few databases for non-speech sound in the real sound scene exist. It is clear that common databases for acoustical signal processing and sound recognition are necessary. Two approaches are taken to build the sound scene database in our project. The first approach is to collect many kinds of non-speech sound. The second approach is to collect three dimensional sound signals accurately by a microphone array. In this paper, the plan and progress of our sound scene database project will be described.