This paper proposes a background noise classifier based on a new, computationally simple, robust set of acoustic features. Complementary to a previous work [1], reporting on the first studies carried out by the authors on background noise classification, this paper mainly presents: 1) a criterion to group a large range of environmental noise into a reduced set of classes of noise with similar acoustic characteristics; 2) a larger set of background noise together with a new multilevel classification architecture; 3) a new set of robust acoustic parameters. We have maintained the pattern recognition approach proposed in [1] in which the matching phase is performed using a set of trained fuzzy rules. The improved version of the Fuzzy Noise Classifier (FNC) has been assessed in terms of misclassification percentage and compared with a Quadratic Gaussian Classifier (QGC).
New Results in Fuzzy Pattern Classification of Background Noise / F., Beritelli; S., Casale; Ruggeri, Giuseppe. - 3:(2000), pp. 1483-1486. (Intervento presentato al convegno ICSP2000) [10.1109/ICOSP.2000.893381].
New Results in Fuzzy Pattern Classification of Background Noise
RUGGERI, Giuseppe
2000-01-01
Abstract
This paper proposes a background noise classifier based on a new, computationally simple, robust set of acoustic features. Complementary to a previous work [1], reporting on the first studies carried out by the authors on background noise classification, this paper mainly presents: 1) a criterion to group a large range of environmental noise into a reduced set of classes of noise with similar acoustic characteristics; 2) a larger set of background noise together with a new multilevel classification architecture; 3) a new set of robust acoustic parameters. We have maintained the pattern recognition approach proposed in [1] in which the matching phase is performed using a set of trained fuzzy rules. The improved version of the Fuzzy Noise Classifier (FNC) has been assessed in terms of misclassification percentage and compared with a Quadratic Gaussian Classifier (QGC).I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.