This paper focuses on recognition of repeats in continuous environmental sounds. Environmental sounds, that are very informative in our daily lives, often repeat several times. Repeat recognition for environmental sounds is essential for compact representation of those sounds and for forecasting the future. In our method, input environmental sound signal is partitioned into several units according to the shapes of the power envelopes, and the auditory distance between every pair of units is computed. Repeating parts are then detected by using the approximate matching algorithm. Experimental results showed the 73.3% of recognition rate in counting the repeats of 30 environmental sounds, the length of each of which ranged from 20 seconds to 2 minutes.
|Number of pages||6|
|Publication status||Published - 2004 Dec 1|
|Event||RO-MAN 2004 - 13th IEEE International Workshop on Robot and Human Interactive Communication - Okayama, Japan|
Duration: 2004 Sep 20 → 2004 Sep 22
|Conference||RO-MAN 2004 - 13th IEEE International Workshop on Robot and Human Interactive Communication|
|Period||04/9/20 → 04/9/22|
ASJC Scopus subject areas