標題: A Two-stage Singing Voice Separation Algorithm Using Spectro-temporal Modulation Features
作者: Yen, Frederick Z.
Huang, Mao-Chang
Chi, Tai-Shih
電機學院
College of Electrical and Computer Engineering
關鍵字: singing voice separation;spectro-temporal modulation;auditory scene analysis
公開日期: 2015
摘要: A two-stage singing voice separation algorithm using spectrotemporal modulation features is proposed in this paper. First, music clips are transformed into auditory spectrograms and the spectral-temporal modulation contents of all time-frequency (T-F) units of the auditory spectrograms are extracted using an auditory model. Then, T-F units are sequentially clustered using the expectation-maximization (EM) algorithm into percussive, harmonic and vocal units through the proposed two-stage algorithm. Lastly, the singing voice is synthesized from clustered vocal T-F units via time-frequency masking. The algorithm was evaluated using the MIR-1K dataset and demonstrated better separation results than our previously proposed one-stage algorithm.
URI: http://hdl.handle.net/11536/136225
ISBN: 978-1-5108-1790-6
期刊: 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5
起始頁: 3321
結束頁: 3324
Appears in Collections:Conferences Paper