Publication Details
Title: Name That Room: Room Identification Using Acoustic Features in a Recording
Author: N. Peters, H. Lei, and G. Friedland
Bibliographic Information: Proceedings of 20th ACM International Conference on Multimedia (MM 2012), pp. 841-844, Nara, Japan
Date: October 2012
Research Area: Audio and Multimedia
Type: Article in conference proceedings
PDF: http://www.icsi.berkeley.edu/pubs/other/ICSI_NameThatRoom2012.pdf
Overview:
This paper presents a system for identifying the room in an audio or video recording through the analysis of acoustical properties. The room identification system was tested using a corpus of 13440 reverberant audio samples. With no common content between the training and testing data, an accuracy of 61% for musical signals and 85% for speech signals was achieved. This approach could be applied in a variety of scenarios where knowledge about the acoustical environment is desired, such as location estimation, music recommendation, or emergency response systems.
Acknowledgements:
This work was partially funded by the Deutscher Akademischer Austausch Diesnst (DAAD) through a postdoctoral fellowship. Additional support was provided by Microsoft through award #024263, Intel through award #024894), matching U.C. Discovery funding (Award #DIG07-10227).
Bibliographic Reference:
N. Peters, H. Lei, and G. Friedland. Name That Room: Room Identification Using Acoustic Features in a Recording. Proceedings of 20th ACM International Conference on Multimedia (MM 2012), pp. 841-844, Nara, Japan, October 2012
Author: N. Peters, H. Lei, and G. Friedland
Bibliographic Information: Proceedings of 20th ACM International Conference on Multimedia (MM 2012), pp. 841-844, Nara, Japan
Date: October 2012
Research Area: Audio and Multimedia
Type: Article in conference proceedings
PDF: http://www.icsi.berkeley.edu/pubs/other/ICSI_NameThatRoom2012.pdf
Overview:
This paper presents a system for identifying the room in an audio or video recording through the analysis of acoustical properties. The room identification system was tested using a corpus of 13440 reverberant audio samples. With no common content between the training and testing data, an accuracy of 61% for musical signals and 85% for speech signals was achieved. This approach could be applied in a variety of scenarios where knowledge about the acoustical environment is desired, such as location estimation, music recommendation, or emergency response systems.
Acknowledgements:
This work was partially funded by the Deutscher Akademischer Austausch Diesnst (DAAD) through a postdoctoral fellowship. Additional support was provided by Microsoft through award #024263, Intel through award #024894), matching U.C. Discovery funding (Award #DIG07-10227).
Bibliographic Reference:
N. Peters, H. Lei, and G. Friedland. Name That Room: Room Identification Using Acoustic Features in a Recording. Proceedings of 20th ACM International Conference on Multimedia (MM 2012), pp. 841-844, Nara, Japan, October 2012