AES E-Library

S. Sofianos, A. Ariyaeeinia, R. Polfreman, and R. Sotudeh, "H-Semantics: A Hybrid Approach to Singing Voice Separation," J. Audio Eng. Soc., vol. 60, no. 10, pp. 831-841, (2012 October.). doi: S. Sofianos, A. Ariyaeeinia, R. Polfreman, and R. Sotudeh, "H-Semantics: A Hybrid Approach to Singing Voice Separation," J. Audio Eng. Soc., vol. 60 Issue 10 pp. 831-841, (2012 October.). doi:
Abstract: Separating the singing voice from accompanying instruments is important in music information-retrieval systems, since it allows for such applications as melody extraction, lyrics recognition, and singer identity. The authors investigate effective methods for unsupervised separation of the singing voice, called H-Semantics (Hybrid Singing Extraction through Multiband Amplitude Enhanced Thresholding and Independent Component Subtraction). The proposed method adds time-domain separation to the previous work that was based on frequency-domain cepstral methods. The results indicate separation of approximately 8.5 dB signal-to-distortion ratio over the baseline.

@article{sofianos2012h-semantics:,
author={sofianos, stratis and ariyaeeinia, aladdin and polfreman, richard and sotudeh, reza},
journal={journal of the audio engineering society},
title={h-semantics: a hybrid approach to singing voice separation},
year={2012},
volume={60},
number={10},
pages={831-841},
doi={},
month={october},} @article{sofianos2012h-semantics:,
author={sofianos, stratis and ariyaeeinia, aladdin and polfreman, richard and sotudeh, reza},
journal={journal of the audio engineering society},
title={h-semantics: a hybrid approach to singing voice separation},
year={2012},
volume={60},
number={10},
pages={831-841},
doi={},
month={october},
abstract={separating the singing voice from accompanying instruments is important in music information-retrieval systems, since it allows for such applications as melody extraction, lyrics recognition, and singer identity. the authors investigate effective methods for unsupervised separation of the singing voice, called h-semantics (hybrid singing extraction through multiband amplitude enhanced thresholding and independent component subtraction). the proposed method adds time-domain separation to the previous work that was based on frequency-domain cepstral methods. the results indicate separation of approximately 8.5 db signal-to-distortion ratio over the baseline.},}

TY - paper
TI - H-Semantics: A Hybrid Approach to Singing Voice Separation
SP - 831 EP - 841
AU - Sofianos, Stratis
AU - Ariyaeeinia, Aladdin
AU - Polfreman, Richard
AU - Sotudeh, Reza
PY - 2012
JO - Journal of the Audio Engineering Society
IS - 10
VO - 60
VL - 60
Y1 - October 2012 TY - paper
TI - H-Semantics: A Hybrid Approach to Singing Voice Separation
SP - 831 EP - 841
AU - Sofianos, Stratis
AU - Ariyaeeinia, Aladdin
AU - Polfreman, Richard
AU - Sotudeh, Reza
PY - 2012
JO - Journal of the Audio Engineering Society
IS - 10
VO - 60
VL - 60
Y1 - October 2012
AB - Separating the singing voice from accompanying instruments is important in music information-retrieval systems, since it allows for such applications as melody extraction, lyrics recognition, and singer identity. The authors investigate effective methods for unsupervised separation of the singing voice, called H-Semantics (Hybrid Singing Extraction through Multiband Amplitude Enhanced Thresholding and Independent Component Subtraction). The proposed method adds time-domain separation to the previous work that was based on frequency-domain cepstral methods. The results indicate separation of approximately 8.5 dB signal-to-distortion ratio over the baseline.