Search Results for author:
Found 8 papers, 0 papers with code
Sound Source Separation Using Latent Variational Block-Wise Disentanglement
In this paper, we present a hybrid classical digital signal processing/deep neural network (DSP/DNN) approach to source separation (SS) highlighting the theoretical link between variational autoencoder and classical approaches to SS.
Real-time Stereo Speech Enhancement with Spatial-Cue Preservation based on Dual-Path Structure
The algorithm runs in real-time on 10-ms frames with a 40 ms of look-ahead.
Neural Harmonium: An Interpretable Deep Structure for Nonlinear Dynamic System Identification with Application to Audio Processing
Improving the interpretability of deep neural networks has recently gained increased attention, especially when the power of deep learning is leveraged to solve problems in physics.
NoLACE: Improving Low-Complexity Speech Codec Enhancement Through Adaptive Temporal Shaping
Speech codec enhancement methods are designed to remove distortions added by speech codecs.
Learning Linear Groups in Neural Networks
Employing equivariance in neural networks leads to greater parameter efficiency and improved generalization performance through the encoding of domain knowledge in the architecture; however, the majority of existing approaches require an a priori specification of the desired symmetries.
Robust Audio Anomaly Detection
The presented approach doesn't assume the presence of labeled anomalies in the training dataset and uses a novel deep neural network architecture to learn the temporal dynamics of the multivariate time series at multiple resolutions while being robust to contaminations in the training dataset.
Enhancing Audio Augmentation Methods with Consistency Learning
For tasks such as classification, there is a good case for learning representations of the data that are invariant to such transformations, yet this is not explicitly enforced by classification losses such as the cross-entropy loss.
PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Loss
Neural network applications generally benefit from larger-sized models, but for current speech enhancement models, larger scale networks often suffer from decreased robustness to the variety of real-world use cases beyond what is encountered in training data.
