Matching entries: 0
settings...
AuthorTitleYearJournal/ProceedingsReftypeDOI/URL
Ward, D., Wierstorf, H., Mason, R., Grais, E.M. and Plumbley, M. BSS Eval or PEASS? Predicting the perception of singing-voice separation 2018 To appear in Proc. ICASSP 2018, Calgary, Canada  misc  
BibTeX:
@misc{Ward2018,
  author = {D. Ward and H. Wierstorf and R.D. Mason and E. M. Grais and M.D. Plumbley},
  title = {BSS Eval or PEASS? Predicting the perception of singing-voice separation},
  year = {2018}
}
Virtanen, T. and Klapuri, A. Separation of harmonic sound sources using sinusoidal modeling 2000
Vol. 22000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (ICASSP), pp. II765-II768 vol.2 
inproceedings DOI  
BibTeX:
@inproceedings{Virtanen2000,
  author = {T. Virtanen and A. Klapuri},
  title = {Separation of harmonic sound sources using sinusoidal modeling},
  booktitle = {2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (ICASSP)},
  year = {2000},
  volume = {2},
  pages = {II765-II768 vol.2},
  doi = {http://doi.org/10.1109/ICASSP.2000.859072}
}
Virtanen, T. Monaural Sound Source Separation by Nonnegative Matrix Factorization With Temporal Continuity and Sparseness Criteria 2007 IEEE Transactions on Audio, Speech, and Language Processing
Vol. 15(3), pp. 1066-1074 
article DOI  
BibTeX:
@article{Virtanen2007,
  author = {T. Virtanen},
  title = {Monaural Sound Source Separation by Nonnegative Matrix Factorization With Temporal Continuity and Sparseness Criteria},
  journal = {IEEE Transactions on Audio, Speech, and Language Processing},
  year = {2007},
  volume = {15},
  number = {3},
  pages = {1066-1074},
  doi = {http://doi.org/10.1109/TASL.2006.885253}
}
E. Vincent, R. Gribonval and C. Fevotte Performance measurement in blind audio source separation 2006 IEEE Transactions on Audio Speech Language Process.
Vol. 14(4), pp. 1462-1469 
article DOI  
BibTeX:
@article{Vincent2006,
  author = {E. Vincent and R. Gribonval and C. Fevotte},
  title = {Performance measurement in blind audio source separation},
  journal = {IEEE Transactions on Audio Speech Language Process.},
  year = {2006},
  volume = {14},
  number = {4},
  pages = {1462--1469},
  doi = {http://doi.org/10.1109/TSA.2005.858005}
}
Uhlich, S., Giron, F. and Mitsufuji, Y. Deep neural network based instrument extraction from music 2015 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2135-2139  inproceedings DOI  
BibTeX:
@inproceedings{Uhlich2015,
  author = {S. Uhlich and F. Giron and Y. Mitsufuji},
  title = {Deep neural network based instrument extraction from music},
  booktitle = {2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year = {2015},
  pages = {2135-2139},
  doi = {http://doi.org/10.1109/ICASSP.2015.7178348}
}
Smaragdis, P., Fevotte, C., Mysore, G.J., Mohammadiha, N. and Hoffman, M. Static and Dynamic Source Separation Using Nonnegative Factorizations: A unified view 2014 IEEE Signal Processing Magazine
Vol. 31(3), pp. 66-75 
article DOI  
BibTeX:
@article{Smaragdis2014,
  author = {P. Smaragdis and C. Fevotte and G. J. Mysore and N. Mohammadiha and M. Hoffman},
  title = {Static and Dynamic Source Separation Using Nonnegative Factorizations: A unified view},
  journal = {IEEE Signal Processing Magazine},
  year = {2014},
  volume = {31},
  number = {3},
  pages = {66-75},
  doi = {http://doi.org/10.1109/MSP.2013.2297715}
}
Serra, X. Musical Sound Modeling with Sinusoids plus Noise 1997 Musical Signal Processing, pp. 91-122  inbook  
Abstract: When generating musical sound on a digital computer, it is important to have a good model whose parameters provide a rich source of meaningful sound transformations. Three basic model types are in prevalent use today for musical sound generation instrument models, spectrum models, and abstract models. Instrument models attempt to parametrize a sound at its source, such as a violin, clarinet, or vocal tract. Spectrum models attempt to parametrize a sound at the basilar membrane of the ear, discarding whatever information the ear seems to discard in the spectrum. Abstract models, such as FM, attempt to provide musically useful parameters in an abstract formula.


This article addresses the second category of synthesis techniques spectrum modeling. The main advantage of this group of techniques is the existence of analysis procedures that extract the synthesis parameters out of real sounds, thus being able to reproduce and modify actual sounds. Our particular approach is based on modeling sounds as stable sinusoids (partials) plus noise (residual component), therefore analyzing sounds with this model and generating new sounds from the analyzed data. The analysis procedure detects partials by studying the time-varying spectral characteristics of a sound and represents them with time-varying sinusoids. These partials are then subtracted from the original sound and the remaining "residual" is represented as a time-varying filtered white noise component. The synthesis procedure is a combination of additive synthesis for the sinusoidal part, and subtractive synthesis for the noise part.


BibTeX:
@inbook{Serra1997,
  author = {X. Serra},
  title = {Musical Sound Modeling with Sinusoids plus Noise},
  booktitle = {Musical Signal Processing},
  publisher = {Swets & Zeitlinger},
  year = {1997},
  pages = {91-122}
}
Rickard, S. The DUET Blind Source Separation Algorithm 2007 Blind Speech Separation, pp. 217-241  inbook DOI URL 
Abstract: This chapter presents a tutorial on the DUET Blind Source Separation method which can separate any number of sources using only two mixtures. The method is valid when sources are W-disjoint orthogonal, that is, when the supports of the windowed Fourier transform of the signals in the mixture are disjoint. For anechoic mixtures of attenuated and delayed sources, the method allows one to estimate the mixing parameters by clustering relative attenuation-delay pairs extracted from the ratios of the time--frequency representations of the mixtures. The estimates of the mixing parameters are then used to partition the time--frequency representation of one mixture to recover the original sources. The technique is valid even in the case when the number of sources is larger than the number of mixtures. The method is particularly well suited to speech mixtures because the time--frequency representation of speech is sparse and this leads to W-disjoint orthogonality. The algorithm is easily coded and a simple Matlab® implementation is presented1. Additionally in this chapter, two strategies which allow DUET to be applied to situations where the microphones are far apart are presented; this removes a major limitation of the original method.
BibTeX:
@inbook{Rickard2007,
  author = {Rickard, Scott},
  title = {The DUET Blind Source Separation Algorithm},
  booktitle = {Blind Speech Separation},
  publisher = {Springer Netherlands},
  year = {2007},
  pages = {217--241},
  url = {https://doi.org/10.1007/978-1-4020-6479-1_8},
  doi = {http://doi.org/10.1007/978-1-4020-6479-1_8}
}
BibTeX:
@article{Rafii2013,
  author = {Z. Rafii and B. Pardo},
  title = {REpeating Pattern Extraction Technique (REPET): A Simple Method for Music/Voice Separation},
  journal = {IEEE Transactions on Audio, Speech & Language Processing},
  year = {2013},
  volume = {21},
  number = {1},
  pages = {71-82}
}
Rafii, Z. and Pardo, B. REpeating Pattern Extraction Technique (REPET): A Simple Method for Music / Voice Separation 2013 IEEE Transactions on Audio, Speech and Language Processing
Vol. 21(1), pp. 73-84 
article  
BibTeX:
@article{Rafii2013a,
  author = {Rafii, Z. and Pardo, B.},
  title = {REpeating Pattern Extraction Technique (REPET): A Simple Method for Music / Voice Separation},
  journal = {IEEE Transactions on Audio, Speech and Language Processing},
  year = {2013},
  volume = {21},
  number = {1},
  pages = {73--84}
}
Ozerov, A. and Févotte, C. Multichannel nonnegative matrix factorization in convolutive mixtures for audio source separation 2010 IEEE Transactions on Audio, Speech and Language Processing
Vol. 18(3), pp. 550-563 
article  
BibTeX:
@article{Ozerov2010,
  author = {A. Ozerov and C. Févotte},
  title = {Multichannel nonnegative matrix factorization in convolutive mixtures for audio source separation},
  journal = {IEEE Transactions on Audio, Speech and Language Processing},
  year = {2010},
  volume = {18},
  number = {3},
  pages = {550--563}
}
Nugraha, A.A., Liutkus, A. and Vincent, E. Multichannel Audio Source Separation With Deep Neural Networks 2016 IEEE/ACM Transactions on Audio, Speech, and Language Processing
Vol. 24(9), pp. 1652-1664 
article DOI  
BibTeX:
@article{Nugraha2016,
  author = {A. A. Nugraha and A. Liutkus and E. Vincent},
  title = {Multichannel Audio Source Separation With Deep Neural Networks},
  journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  year = {2016},
  volume = {24},
  number = {9},
  pages = {1652-1664},
  doi = {http://doi.org/10.1109/TASLP.2016.2580946}
}
Luo, Y., Chen, Z., Hershey, J.R., Roux, J.L. and Mesgarani, N. Deep Clustering and Conventional Networks for Music Separation: Stronger Together 2017 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (ICASSP)  inproceedings  
BibTeX:
@inproceedings{Luo16,
  author = {Y. Luo and Z. Chen and J. R. Hershey and J. Le Roux and N. Mesgarani},
  title = {Deep Clustering and Conventional Networks for Music Separation: Stronger Together},
  booktitle = {2017 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (ICASSP)},
  year = {2017}
}
Liutkus, A., Stöter, F.-R., Rafii, Z., Kitamura, D., Rivet, B., Ito, N., Ono, N. and Fontecave, J. The 2016 signal separation evaluation campaign 2017 International Conference on Latent Variable Analysis and Signal Separation, pp. 323-332  inproceedings  
BibTeX:
@inproceedings{sisec2016,
  author = {A. Liutkus and F.-R. Stöter and Z. Rafii and D. Kitamura and B. Rivet and N. Ito and N. Ono and J. Fontecave},
  title = {The 2016 signal separation evaluation campaign},
  booktitle = {International Conference on Latent Variable Analysis and Signal Separation},
  year = {2017},
  pages = {323--332}
}
Liutkus, A., Fitzgerald, D., Rafii, Z., Pardo, B. and Daudet, L. Kernel Additive Models for Source Separation 2014 IEEE Transactions on Signal Processing
Vol. 62(16), pp. 4298-4310 
article DOI  
BibTeX:
@article{Liutkus2014,
  author = {A. Liutkus and D. Fitzgerald and Z. Rafii and B. Pardo and L. Daudet},
  title = {Kernel Additive Models for Source Separation},
  journal = {IEEE Transactions on Signal Processing},
  year = {2014},
  volume = {62},
  number = {16},
  pages = {4298-4310},
  doi = {http://doi.org/10.1109/TSP.2014.2332434}
}
Lee, D.D., Laboratories, B., Hill, M. and Seung, H.S. Algorithms for Non-negative Matrix Factorization 2001 (1)Advances in Neural Information Processing Systems 13, pp. 556-562  inproceedings  
BibTeX:
@inproceedings{Lee2001,
  author = {Lee, D. D and Laboratories, Bell and Hill, Murray and H S. Seung},
  title = {Algorithms for Non-negative Matrix Factorization},
  booktitle = {Advances in Neural Information Processing Systems 13},
  publisher = {MIT Press},
  year = {2001},
  number = {1},
  pages = {556--562}
}
ITU-R Recommendation BS.1534-3: Method for the subjective assessment of indermediate quality levels of coding systems 10/2015 (BS.1534)  misc  
BibTeX:
@misc{ITUR.062014,
  author = {ITU-R},
  title = {Recommendation BS.1534-3: Method for the subjective assessment of indermediate quality levels of coding systems},
  year = {10/2015},
  number = {BS.1534},
  edition = {3}
}
Huang, P.-S., Chen, S.D., Smaragdis, P. and Hasegawa-Johnson, M. Singing-Voice Separation From Monaural Recordings Using Robust Principal Component Analysis 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 57-60  inproceedings  
BibTeX:
@inproceedings{Huang2012,
  author = {P.-S. Huang and S. D. Chen and P. Smaragdis and M. Hasegawa-Johnson},
  title = {Singing-Voice Separation From Monaural Recordings Using Robust Principal Component Analysis},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year = {2012},
  pages = {57--60}
}
Huang, P.S., Kim, M., Hasegawa-Johnson, M. and Smaragdis, P. Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation 2015 IEEE/ACM Transactions on Audio, Speech, and Language Processing
Vol. 23(12), pp. 2136-2147 
article DOI  
BibTeX:
@article{Huang2015,
  author = {P. S. Huang and M. Kim and M. Hasegawa-Johnson and P. Smaragdis},
  title = {Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation},
  journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  year = {2015},
  volume = {23},
  number = {12},
  pages = {2136-2147},
  doi = {http://doi.org/10.1109/TASLP.2015.2468583}
}
FitzGerald, D., Liutkus, A. and Badeau, R. Projection-Based Demixing of Spatial Audio 2016 IEEE/ACM Transactions on Audio, Speech, and Language Processing
Vol. 24(9), pp. 1560-1572 
article DOI  
BibTeX:
@article{Fitzgerald2016,
  author = {D. FitzGerald and A. Liutkus and R. Badeau},
  title = {Projection-Based Demixing of Spatial Audio},
  journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  year = {2016},
  volume = {24},
  number = {9},
  pages = {1560-1572},
  doi = {http://doi.org/10.1109/TASLP.2016.2570945}
}
FitzGerald, D. Harmonic/Percusssive Separation Using Median Filtering 2010 Proceedings of the 13th International Conference on Digital Audio Effects (DAFx)  inproceedings URL 
BibTeX:
@inproceedings{FitzGerald2010,
  author = {FitzGerald, D.},
  title = {Harmonic/Percusssive Separation Using Median Filtering},
  booktitle = {Proceedings of the 13th International Conference on Digital Audio Effects (DAFx)},
  year = {2010},
  url = {http://dafx10.iem.at/proceedings/papers/DerryFitzGerald_DAFx10_P15.pdf}
}
Fitzgerald, D. Harmonic/percussive separation using median filtering 2010 13th Int. Conference on Digital Audio Effects (DAFx-10)  inproceedings  
BibTeX:
@inproceedings{Fitzgerlad2010,
  author = {D. Fitzgerald},
  title = {Harmonic/percussive separation using median filtering},
  booktitle = {13th Int. Conference on Digital Audio Effects (DAFx-10)},
  year = {2010}
}
Ewert, S., Pardo, B., Mueller, M. and Plumbley, M.D. Score-Informed Source Separation for Musical Audio Recordings: An overview 2014 IEEE Signal Processing Magazine
Vol. 31(3), pp. 116-124 
article DOI  
BibTeX:
@article{Ewert2014,
  author = {S. Ewert and B. Pardo and M. Mueller and M. D. Plumbley},
  title = {Score-Informed Source Separation for Musical Audio Recordings: An overview},
  journal = {IEEE Signal Processing Magazine},
  year = {2014},
  volume = {31},
  number = {3},
  pages = {116-124},
  doi = {http://doi.org/10.1109/MSP.2013.2296076}
}
Emiya, V., Vincent, E., Harlander, N. and Hohmann, V. Subjective and Objective Quality Assessment of Audio Source Separation 2011 IEEE Transactions on Audio, Speech, and Language Processing
Vol. 19(7), pp. 2046-2057 
article DOI  
BibTeX:
@article{Emiya2011,
  author = {Emiya, V. and Vincent, E. and Harlander, N. and Hohmann, V.},
  title = {Subjective and Objective Quality Assessment of Audio Source Separation},
  journal = {IEEE Transactions on Audio, Speech, and Language Processing},
  year = {2011},
  volume = {19},
  number = {7},
  pages = {2046--2057},
  doi = {http://doi.org/10.1109/TASL.2011.2109381}
}
Durrieu, J.L., Richard, G., David, B. and Fevotte, C. Source/Filter Model for Unsupervised Main Melody Extraction From Polyphonic Audio Signals 2010 IEEE Transactions on Audio, Speech, and Language Processing
Vol. 18(3), pp. 564-575 
article DOI  
BibTeX:
@article{Durrieu2010,
  author = {J. L. Durrieu and G. Richard and B. David and C. Fevotte},
  title = {Source/Filter Model for Unsupervised Main Melody Extraction From Polyphonic Audio Signals},
  journal = {IEEE Transactions on Audio, Speech, and Language Processing},
  year = {2010},
  volume = {18},
  number = {3},
  pages = {564-575},
  doi = {http://doi.org/10.1109/TASL.2010.2041114}
}
Duong, N., Vincent, E. and Gribonval, R. Under-Determined Reverberant Audio Source Separation Using a Full-Rank Spatial Covariance Model 2010 IEEE Transactions on Audio, Speech, and Language Processing
Vol. 18(7), pp. 1830 -1840 
article DOI  
BibTeX:
@article{Duong2010,
  author = {Duong, N.Q.K. and Vincent, E. and Gribonval, R.},
  title = {Under-Determined Reverberant Audio Source Separation Using a Full-Rank Spatial Covariance Model},
  journal = {IEEE Transactions on Audio, Speech, and Language Processing},
  year = {2010},
  volume = {18},
  number = {7},
  pages = {1830 -1840},
  doi = {http://doi.org/10.1109/TASL.2010.2050716}
}
Chan, T.-S., Yeh, T.-C., Fan, Z.-C., Chen, H.-W., Su, L., Yang, Y.-H. and Jang, R. Vocal activity informed singing voice separation with the iKala dataset 2015 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 718-722  inproceedings  
BibTeX:
@inproceedings{Chan2015,
  author = {T.-S. Chan and T.-C. Yeh and Z.-C. Fan and H.-W. Chen and L. Su and Y.-H. Yang and R. Jang},
  title = {Vocal activity informed singing voice separation with the iKala dataset},
  booktitle = {2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year = {2015},
  pages = {718--722}
}
Cano, E., Plumbley, M. and Dittmar, C. Phase-based harmonic/percussive separation 2014 15th Annual Conference of the International Speech Communication Association (2014). Interspeech  inproceedings  
BibTeX:
@inproceedings{Cano2014,
  author = {Cano, E. and Plumbley, M. and Dittmar, C.},
  title = {Phase-based harmonic/percussive separation},
  booktitle = {15th Annual Conference of the International Speech Communication Association (2014). Interspeech},
  year = {2014}
}
Cano, E., FitzGerald, D. and Brandenburg, K. Evaluation of quality of sound source separation algorithms: Human perception vs quantitative metrics 2016 2016 24th European Signal Processing Conference (EUSIPCO), pp. 1758-1762  inproceedings  
BibTeX:
@inproceedings{Cano2016,
  author = {Cano, E. and FitzGerald, D. and Brandenburg, K.},
  title = {Evaluation of quality of sound source separation algorithms: Human perception vs quantitative metrics},
  booktitle = {2016 24th European Signal Processing Conference (EUSIPCO)},
  year = {2016},
  pages = {1758--1762}
}
Bregman, A.S. Auditory Scene Analysis: The Perceptual Organization of Sound 1990   book  
BibTeX:
@book{Bregman:1990:BOOK,
  author = {Bregman, Albert S.},
  title = {Auditory Scene Analysis: The Perceptual Organization of Sound},
  publisher = {MIT Press/Bradford Books},
  year = {1990}
}
Barry, D., Lawlor, B. and Coyle, E. Real-time Sound Source Separation using Azimuth Discrimination and Resynthesis 2004 117th Audio Engineering Society (AES) Convention  inproceedings  
BibTeX:
@inproceedings{Barry2004,
  author = {D. Barry and B. Lawlor and E. Coyle},
  title = {Real-time Sound Source Separation using Azimuth Discrimination and Resynthesis},
  booktitle = {117th Audio Engineering Society (AES) Convention},
  year = {2004}
}