479 citations · 1.5k across the 53 of their papers we have counts for
12 papers · 1 filter
Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexity
Ahmed Mustafa, Jean-Marc Valin, Jan Büthe +2
GAN vocoders are currently one of the state-of-the-art methods for building high-quality neural waveform generative models. However, most of their architectures require dozens of b…
Optimal Condition Training for Target Source Separation
Efthymios Tzinis, Gordon Wichern, Paris Smaragdis +1
Recent research has shown remarkable performance in leveraging multiple extraneous conditional and non-mutually exclusive semantic concepts for sound source separation, allowing th…
Latent Iterative Refinement for Modular Source Separation
Dimitrios Bralios, Efthymios Tzinis, Gordon Wichern +2
Traditional source separation approaches train deep neural network models end-to-end with all the data available at once by minimizing the empirical risk on the whole training set.…
Meta-Learning for Adaptive Filters with Higher-Order Frequency Dependencies
Junkai Wu, Jonah Casebeer, Nicholas J. Bryan +1
Adaptive filters are applicable to many signal processing tasks including acoustic echo cancellation, beamforming, and more. Adaptive filters are typically controlled using algorit…
Don't Look Up: Ubiquitous Data Exfiltration Pathways in Commercial Spaces
Anku Adhikari, Samuel Guo, Paris Smaragdis +1
We show that as a side effect of building code requirements, almost all commercial buildings today are vulnerable to a novel data exfiltration attack, even if they are air-gapped a…
Semi-supervised Time Domain Target Speaker Extraction with Attention
Zhepei Wang, Ritwik Giri, Shrikant Venkataramani +5
In this work, we propose Exformer, a time-domain architecture for target speaker extraction. It consists of a pre-trained speaker embedder network and a separator network based on…
Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model
Jean-Marc Valin, Ahmed Mustafa, Christopher Montgomery +4
As deep speech enhancement algorithms have recently demonstrated capabilities greatly surpassing their traditional counterparts for suppressing noise, reverberation and echo, atten…
Learning Representations for New Sound Classes With Continual Self-Supervised Learning
Zhepei Wang, Cem Subakan, Xilin Jiang +4
In this paper, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without…
Meta-AF: Meta-Learning for Adaptive Filters
Jonah Casebeer, Nicholas J. Bryan, Paris Smaragdis
Adaptive filtering algorithms are pervasive throughout signal processing and have had a material impact on a wide variety of domains including audio processing, telecommunications,…
End-to-end LPCNet: A Neural Vocoder With Fully-Differentiable LPC Estimation
Krishna Subramani, Jean-Marc Valin, Umut Isik +2
Neural vocoders have recently demonstrated high quality speech synthesis, but typically require a high computational complexity. LPCNet was proposed as a way to reduce the complexi…
Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet
Jean-Marc Valin, Umut Isik, Paris Smaragdis +1
Neural speech synthesis models can synthesize high quality speech but typically require a high computational complexity to do so. In previous work, we introduced LPCNet, which uses…
RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing
Efthymios Tzinis, Yossi Adi, Vamsi Krishna Ithapu +3
We present RemixIT, a simple yet effective self-supervised method for training speech enhancement without the need of a single isolated in-domain speech nor a noise waveform. Our a…