Exploring Perceptual Based Timbre Feature for Singer Identification
- Cite this paper as:
- Kalayar Khine S.Z., Nwe T.L., Li H. (2008) Exploring Perceptual Based Timbre Feature for Singer Identification. In: Kronland-Martinet R., Ystad S., Jensen K. (eds) Computer Music Modeling and Retrieval. Sense of Sounds. CMMR 2007. Lecture Notes in Computer Science, vol 4969. Springer, Berlin, Heidelberg
Timbre can be defined as feature of an auditory stimulus that allows us to distinguish the sounds which have the same pitch and loudness. In this paper, we explore timbre based perceptual feature for singer identification. We start with a vocal detection process to extract the vocal segments from the sound. The cepstral coefficients, which reflect timbre characteristics, are then computed from the vocal segments. The cepstral coefficients of timbre are formulated by combining information of harmonic and the dynamic characteristics of the sound such as vibrato and the attack-decay envelope of the songs. Bandpass filters that spread according to the octave frequency scale are used to extract vibrato and harmonic information of sounds. The experiments are conducted on a database of 84 popular songs. The results show that the proposed timbre based perceptual feature is robust and effective. We achieve an average error rate of 12.2% in segment level singer identification.
KeywordsTimbre Singing Voice Detection Vibrato Harmonic
Unable to display preview. Download preview PDF.