A database of clean and noisy speech for audio research
Clone or download
Latest commit 8f02d11 Jan 26, 2018
Type Name Latest commit message Commit time
Failed to load latest commit information.
data added wave files Jan 26, 2018
README.md Update README.md Jan 26, 2018
details.md more details Jan 26, 2018


original source: http://web.archive.org/web/20060831010952/http://cslu.ece.ogi.edu/nsel/data/SpEAR_database.html

SpEAR (Speech Enhancement and Assessment Resource) Database

http://ee.ogi.edu/NSEL/ (Beta Release v1.0)

The SpEAR Database contains carefully selected samples of noise corrupted speech with clean speech references. This beta version is a small initial release of the database to allow feedback for future developments of this resource.

All speech and noise sources have been acoustically combined and re-recorded. Synchronous clocking is used to provide an exact time-aligned reference to the clean speech signal (see Technical Details).


Contents (more detailed description)

  • Original Speech Files (TIMIT/)

  • Noisy Speech Recordings (Noisy_Recordings/)- Recorded speech and recorded noise: acoustically combined and re-recorded. Various noise sources and different SNR levels.

  • Lombard Speech (Lombard/) - Live speech in a noisy environment. Recorded noise sources are used to allow extraction of a cleaned speech reference.

  • Monaural Recordings (Monaural/) - Two recorded speech signals: acoustically combined and re-recorded.

Future releases will contain a more substantial number of samples, additional additive noise sources, cellular and coding noise, etc.

Use of this data is free, but should be referenced in all publications as follows:

Speech Enhancement Assessment Resource (SpEAR) Database. http://ee.ogi.edu/NSEL/. Beta Release v1.0. CSLU, Oregon Graduate Institute of Science and Technology. E. Wan, A. Nelson, and Rick Peterson.


Principle Investigator:

Graduate Research Assistants:

  • Houwu Bai

  • Rudolph van der Merwe

  • Alex T. Nelson (graduated 2000)