Convolutive Speech Bases and Their Application to Supervised Speech Separation von Smaragdis, P.

Volltext

Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization von Mohammadiha, Nasser, Smaragdis, Paris, Leijon, Arne

Volltext

Compute and Memory Efficient Universal Sound Source Separation von Tzinis, Efthymios, Wang, Zhepei, Jiang, Xilin, Smaragdis, Paris

Volltext

Non-negative Matrix Factor Deconvolution; Extraction of Multiple Sound Sources from Monophonic Inputs von Smaragdis, Paris

Volltext

RemixIT: Continual Self-Training of Speech Enhancement Models via Bootstrapped Remixing von Tzinis, Efthymios, Adi, Yossi, Ithapu, Vamsi K., Xu, Buye, Smaragdis, Paris, Kumar, Anurag

Volltext

Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation von Po-Sen Huang, Minje Kim, Hasegawa-Johnson, Mark, Smaragdis, Paris

Volltext

Learning Representations for New Sound Classes With Continual Self-Supervised Learning von Wang, Zhepei, Subakan, Cem, Jiang, Xilin, Wu, Junkai, Tzinis, Efthymios, Ravanelli, Mirco, Smaragdis, Paris

Volltext

Mixtures of Local Dictionaries for Unsupervised Speech Enhancement von Minje Kim, Smaragdis, Paris

Volltext

A Wrapped Kalman Filter for Azimuthal Speaker Tracking von Traa, Johannes, Smaragdis, Paris

Volltext

Meta-AF: Meta-Learning for Adaptive Filters von Casebeer, Jonah, Bryan, Nicholas J., Smaragdis, Paris

Volltext

Blind separation of convolved mixtures in the frequency domain von Smaragdis, Paris

Volltext

Neural acoustic fields von Smaragdis, Paris

Volltext

Singing-voice separation from monaural recordings using robust principal component analysis von Po-Sen Huang, Chen, S. D., Smaragdis, P., Hasegawa-Johnson, M.

Volltext

Position and Trajectory Learning for Microphone Arrays von Smaragdis, P., Boufounos, P.

Volltext

Probabilistic Latent Variable Models as Nonnegative Factorizations von Shashanka, Madhusudana, Raj, Bhiksha, Smaragdis, Paris

Volltext

Robust Source Localization and Enhancement With a Probabilistic Steered Response Power Model von Traa, Johannes, Wingate, David, Stein, Noah D., Smaragdis, Paris

Volltext

Sparse and shift-invariant feature extraction from non-negative data von Smaragdis, P., Raj, B., Shashanka, M.

Volltext

End-to-end music transcription using a neural network von Smaragdis, Paris

Volltext

Separation by "humming": User-guided sound extraction from monophonic mixtures von Smaragdis, P., Mysore, G.J.

Volltext

Optimal cost function and magnitude power for NMF-based speech separation and music interpolation von King, B., Fevotte, C., Smaragdis, P.

Volltext