Tách nguồn âm thanh sử dụng mô hình phổ nguồn tổng quát trên cơ sở thừa số hóa ma trận không âm (Luận án tiến sĩ)

y trained recurrent neural networks for single-channel speech separation. In
IEEE Global Conference on Signal and Information Processing, pages 577–581.
[151] Winter, S., Kellermann, W., Sawada, H., and Makino, S. (2006). MAP-based
underdetermined blind source separation of convolutive mixtures by hierarchical
clustering and

1 -norm

minimization. EURASIP Journal on Advances in Signal

Processing, 2007(1):024717.
[152] Wlfel, M. and McDonough, J. (2009). Distant speech recognition. Wiley,
Chichester, U.K.
[153] Wood, S. and Rouat, J. (2016). Blind speech separation with GCC-NMF. In
Proc. Interspeech, pages 3329–3333.
[154] Wood, S. U. N., Rouat, J., Dupont, S., and Pironkov, G. (2017). Blind Speech
Separation and Enhancement With GCC-NMF. IEEE/ACM Transactions on Audio,
Speech, and Language Processing, 25(4):745–755.
[155] Xiao, X., Watanabe, S., Erdogan, H., Lu, L., Hershey, J., Seltzer, M. L., Chen,
G., Zhang, Y., Mandel, M., and Yu, D. (2016). Deep beamforming networks for
111


multi-channel speech recognition. In IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP), pages 5745–5749. IEEE.
[156] Yilmaz, Y. K., Cemgil, A. T., and Simsekli, U. (2011). Generalised coupled
tensor factorisation. In Proceedings of the 24th International Conference on Neural
Information Processing Systems, NIPS’11, pages 2151–2159, USA. Curran Associates Inc.
[157] Yu, D. and Deng, L. (2011). Deep Learning and Its Applications to Signal
and Information Processing [Exploratory DSP. IEEE Signal Processing Magazine,
28(1):145–154.

[158] Zdunek, R. (2011). Convolutive nonnegative matrix factorization with markov
random field smoothing for blind unmixing of multichannel speech recordings. In
Proc. The 5th International Conference on Advances in Nonlinear Speech Processing, NOLISP’11, pages 25–32. Springer-Verlag.
[159] Zdunek, R. (2013). Improved Convolutive and Under-Determined Blind Audio
Source Separation with MRF Smoothing. Cognitive Computation, 5(4):493–503.
[160] Zhang, Z.-Y. (2012). Nonnegative Matrix Factorization: Models, Algorithms
and Applications. In Data Mining: Foundations and Intelligent Paradigms, volume 24, pages 99–134. Springer Berlin Heidelberg.

112


LIST OF PUBLICATIONS
1. Hien-Thanh Thi Duong, Quoc-Cuong Nguyen, Cong-Phuong Nguyen,
Thanh Huan Tran, and Ngoc Q. K. Duong (2015). Speech enhancement based on nonnegative matrix factorization with mixed group sparsity constraint. Proc. ACM International Symposium on Information
and Communication Technology (SoICT 2015), pp. 247-251, Hue,
Vietnam. ISBN 978-1-4503-3843-1, DOI:10.1145/2833258.2833276.
2. Hien-Thanh Thi Duong, Quoc-Cuong Nguyen, Cong-Phuong Nguyen,
and Ngoc Q. K. Duong (2016). Single-channel speaker-dependent
speech enhancement exploiting generic noise model learned by nonnegative matrix factorization. Proc. IEEE International Conference on
Electronics, Information and Communication, pp. 268-271, Danang,
Vietnam, Electronic ISBN 978-1-4673-8016-4, PoD ISBN 978-1-46738017-1, DOI 10.1109/ELINFOCOM.2016.7562952.
3. Thanh Thi Hien Duong, Nobutaka Ono, Yasutaka Nakajima and
Toshiya Ohshima (2016). Non-stationary Segment Detection Methods based on Single-basis Non-negative Matrix Factorization for Effective Annotation. Proc. IEEE Asia-Pacific Signal and Information
Processing Association Annual Summit Conference (IEEE APSIPA
ASC), pp. 1-6, Jeju, Korea, Electronic ISBN 978-9-8814-7682-1, PoD
ISBN 978-1-5090-2401-8, DOI 10.1109/APSIPA.2016.7820760.
4. Thanh Thi Hien Duong, Phuong Cong Nguyen, and Cuong Quoc
Nguyen (2018). Exploiting Nonnegative Matrix Factorization with
Mixed Group Sparsity Constraint to Separate Speech Signal from Singlechannel Mixture with Unknown Ambient Noise. EAI Endorsed Transactions on Context-Aware Systems and Applications. vol. 18(13), pp.
1-8. ISSN 2409-0026.

5. Duong Thi Hien Thanh, Nguyen Cong Phuong, and Nguyen Quoc
Cuong (2018). Combination of Nonnegative Matrix Factorization and
mixed group sparsity constraint to exploit generic source spectral model
in single-channel audio source separation. Journal of Military Science
and Technology. Vol. 45(4), pp: 83-94. ISSN 1859 - 1043 (In Viet-

113


namese).
6. Thanh Thi Hien Duong, Ngoc Q. K. Duong, Phuong Cong Nguyen,
and Cuong Quoc Nguyen (2018). Multichannel source separation exploiting NMF-based generic source spectral model in Gaussian modeling framework. In Latent Variable Analysis and Signal Separation,
vol. 10891, pp. 547-557. Springer International Publishing. DOI
10.1007/9 78-3-319-93764-9 50 (SCOPUS).
7. Thanh Thi Hien Duong, Ngoc Q. K. Duong, Phuong Cong Nguyen,
and Cuong Quoc Nguyen (2019). Gaussian modeling-based multichannel audio source separation exploiting generic source spectral
model. IEEE/ACM Transactions on Audio, Speech, and Language
Processing, vol. 27(1), pp. 32-43. ISSN 2329-9304, DOI 10.1109/TASLP.2018.28 69692 (ISI - Q1).

114