End-to-end Networks for Supervised Single-channel Speech Separation von Venkataramani, Shrikant, Smaragdis, Paris

Volltext bestellen

Self-supervised Learning for Speech Enhancement von Wang, Yu-Che, Venkataramani, Shrikant, Smaragdis, Paris

Volltext bestellen

A Neural Network Alternative to Non-Negative Audio Models von Smaragdis, Paris, Venkataramani, Shrikant

Volltext bestellen

End-to-end Non-Negative Autoencoders for Sound Source Separation von Venkataramani, Shrikant, Tzinis, Efthymios, Smaragdis, Paris

Volltext bestellen

A Style Transfer Approach to Source Separation von Venkataramani, Shrikant, Tzinis, Efthymios, Smaragdis, Paris

Volltext bestellen

To Dereverb Or Not to Dereverb? Perceptual Studies On Real-Time Dereverberation Targets von Valin, Jean-Marc, Giri, Ritwik, Venkataramani, Shrikant, Isik, Umut, Krishnaswamy, Arvindh

Volltext bestellen

Efficient Trainable Front-Ends for Neural Speech Enhancement von Casebeer, Jonah, Isik, Umut, Venkataramani, Shrikant, Krishnaswamy, Arvindh

Volltext bestellen

Performance Based Cost Functions for End-to-End Speech Separation von Venkataramani, Shrikant, Higa, Ryley, Smaragdis, Paris

Volltext bestellen

Semi-supervised Time Domain Target Speaker Extraction with Attention von Wang, Zhepei, Giri, Ritwik, Venkataramani, Shrikant, Isik, Umut, Valin, Jean-Marc, Smaragdis, Paris, Goodwin, Mike, Krishnaswamy, Arvindh

Volltext bestellen

End-to-end Networks for Supervised Single-channel Speech Separation von Venkataramani, Shrikant, Paris Smaragdis

Volltext

Personalized PercepNet: Real-time, Low-complexity Target Voice Separation and Enhancement von Giri, Ritwik, Venkataramani, Shrikant, Valin, Jean-Marc, Isik, Umut, Krishnaswamy, Arvindh

Volltext bestellen

Neural Network Alternatives to Convolutive Audio Models for Source Separation von Venkataramani, Shrikant, Subakan, Y. Cem, Smaragdis, Paris

Volltext bestellen

End-to-end Source Separation with Adaptive Front-Ends von Venkataramani, Shrikant, Casebeer, Jonah, Smaragdis, Paris

Volltext bestellen

Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information von Tzinis, Efthymios, Venkataramani, Shrikant, Paris Smaragdis

Volltext

Class-conditional embeddings for music source separation von Seetharaman, Prem, Wichern, Gordon, Venkataramani, Shrikant, Roux, Jonathan Le

Volltext bestellen

Self-supervised Learning for Speech Enhancement von Yu-Che, Wang, Venkataramani, Shrikant, Paris Smaragdis

Volltext

Two-Step Sound Source Separation: Training on Learned Latent Targets von Tzinis, Efthymios, Venkataramani, Shrikant, Wang, Zhepei, Subakan, Cem, Paris Smaragdis

Volltext

A Neural Network Alternative to Non-Negative Audio Models von Paris Smaragdis, Venkataramani, Shrikant

Volltext

End-to-end Non-Negative Autoencoders for Sound Source Separation von Venkataramani, Shrikant, Tzinis, Efthymios, Paris Smaragdis

Volltext

Automatic voiceover correction system von Venkataramani, Shrikant, Smaragdis, Paris, Mysore, Gautham

Volltext bestellen