Audio classification from time-frequency texture
Time-frequency representations of audio signals often resemble texture images. This paper derives a simple audio classification algorithm based on treating sound spectrograms as texture images. The algorithm is inspired by an earlier visual classification scheme particularly efficient at classifying...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2012
|
| Online Access: | http://hdl.handle.net/1721.1/74538 https://orcid.org/0000-0002-7161-7812 |
| _version_ | 1811091870565007360 |
|---|---|
| author | Slotine, Jean-Jacques E. Yu, Guoshen |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Slotine, Jean-Jacques E. Yu, Guoshen |
| author_sort | Slotine, Jean-Jacques E. |
| collection | MIT |
| description | Time-frequency representations of audio signals often resemble texture images. This paper derives a simple audio classification algorithm based on treating sound spectrograms as texture images. The algorithm is inspired by an earlier visual classification scheme particularly efficient at classifying textures. While solely based on time-frequency texture features, the algorithm achieves surprisingly good performance in musical instrument classification experiments. |
| first_indexed | 2024-09-23T15:09:20Z |
| format | Article |
| id | mit-1721.1/74538 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:09:20Z |
| publishDate | 2012 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/745382022-09-29T13:03:13Z Audio classification from time-frequency texture Slotine, Jean-Jacques E. Yu, Guoshen Massachusetts Institute of Technology. Department of Mechanical Engineering Slotine, Jean-Jacques E. Time-frequency representations of audio signals often resemble texture images. This paper derives a simple audio classification algorithm based on treating sound spectrograms as texture images. The algorithm is inspired by an earlier visual classification scheme particularly efficient at classifying textures. While solely based on time-frequency texture features, the algorithm achieves surprisingly good performance in musical instrument classification experiments. 2012-10-31T20:52:23Z 2012-10-31T20:52:23Z 2009-05 2009-04 Article http://purl.org/eprint/type/ConferencePaper 978-1-4244-2354-5 978-1-4244-2353-8 1520-6149 http://hdl.handle.net/1721.1/74538 Guoshen, Yu, and Slotine, Jean-Jacques E. "Audio classification from time-frequency texture." IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2009) (2009): 1677-1680. © 2009 IEEE https://orcid.org/0000-0002-7161-7812 en_US http://dx.doi.org/10.1109/ICASSP.2009.4959924 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2009) Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Institute of Electrical and Electronics Engineers (IEEE) IEEE |
| spellingShingle | Slotine, Jean-Jacques E. Yu, Guoshen Audio classification from time-frequency texture |
| title | Audio classification from time-frequency texture |
| title_full | Audio classification from time-frequency texture |
| title_fullStr | Audio classification from time-frequency texture |
| title_full_unstemmed | Audio classification from time-frequency texture |
| title_short | Audio classification from time-frequency texture |
| title_sort | audio classification from time frequency texture |
| url | http://hdl.handle.net/1721.1/74538 https://orcid.org/0000-0002-7161-7812 |
| work_keys_str_mv | AT slotinejeanjacquese audioclassificationfromtimefrequencytexture AT yuguoshen audioclassificationfromtimefrequencytexture |