Separation of Singing Voice from Music Accompaniment with Unvoiced Sounds Reconstruction for Monaural Recordings

Hsu CL, Jang JSR, Tsai TL. Separation of Singing Voice from Music Accompaniment with Unvoiced Sounds Reconstruction for Monaural Recordings. In: AES Convention 125. Audio Engineering Society; 2008. Paper 7633. Available from: https://aes.org/publications/elibrary-page/?id=14784

@inproceedings{Hsu2008_14784,
  author = {Hsu, Chao-Ling and Jang, Jyh-Shing Roger and Tsai, Te-Lu},
  title = {{Separation of Singing Voice from Music Accompaniment with Unvoiced Sounds Reconstruction for Monaural Recordings}},
  booktitle = {AES Convention 125},
  note = {Paper 7633},
  year = {2008},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=14784}
}

TY  - CPAPER
TI  - Separation of Singing Voice from Music Accompaniment with Unvoiced Sounds Reconstruction for Monaural Recordings
AU  - Hsu, Chao-Ling
AU  - Jang, Jyh-Shing Roger
AU  - Tsai, Te-Lu
T2  - AES Convention 125
M1  - Paper 7633
PY  - 2008
DA  - 2008/10/06
UR  - https://aes.org/publications/elibrary-page/?id=14784
PB  - Audio Engineering Society
LA  - en
AB  - Separating singing voice from music accompaniment is an appealing but challenging problem, especially in the monaural case. One existing approach is based on computational audio scene analysis which uses pitch as the cue to resynthesize the singing voice. However, the unvoiced parts of the singing voice are totally ignored since they have no pitch at all. This paper proposes a method to detect unvoiced parts of an input signal and to resynthesize them without using pitch information. The experimental result demonstrates that the unvoiced parts can be reconstructed successfully, with 3.28 dB signal-to-noise ratio higher than that achieved by the currently state-of-the-art method in the literature.
ER  -