Name
Abstract | ||
|---|---|---|
Singing voice separation from accompaniment in monaural music recordings is a crucial technique in music information retrieval. A majority of existing algorithms are based on singing pitch detection, and take the detected pitch as the cue to identify and separate the harmonic structure of the singing voice. However, as a key yet undependable premise, vocal pitch detection makes the separation performance of these algorithms rather limited. To overcome the inherent weakness of pitch-based inference algorithms, two novel methods based on non-negative matrix factorization (NMF) are devised in this paper. The first one combines NMF with the distribution regularities of vocals under different time frequency resolutions, so that many vocal unrelated portions are eliminated and the singing voice is hence enhanced. In consequence, the accuracy of vocal pitch detection is significantly improved. The second method applies NMF to decompose the spectrogram into non-overlapping and indivisible segments, which can be used as another cue besides the pitch to help identify the vocal harmonic structure. The two proposed methods are integrated into the framework of pitch-based inference. Extensive testing on the MIR-1K public dataset shows that both of them are rather effective, and the overall performances outperform other state-of-the-art singing separation algorithms. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1145/2733373.2806257 | ACM Multimedia |
Keywords | Field | DocType |
Singing voice separation,pitch-based inference,singing pitch detection,non-negative matrix factorization (NMF) | Music information retrieval,Computer science,Inference,Spectrogram,Matrix decomposition,Speech recognition,Singing,Non-negative matrix factorization,Pitch detection algorithm,Monaural | Conference |
Citations | PageRank | References |
1 | 0.34 | 19 |
Authors | ||
3 | ||