Search Results for author:
Found 36 papers, 8 papers with code
Meta-Heuristic Fronthaul Bit Allocation for Cell-free Massive MIMO Systems
Limited capacity of fronthaul links in a cell-free massive multiple-input multiple-output (MIMO) system can cause quantization errors at a central processing unit (CPU) during data transmission, complicating the centralized rate optimization problem.
BiTT: Bi-directional Texture Reconstruction of Interacting Two Hands from a Single Image
Creating personalized hand avatars is important to offer a realistic experience to users on AR / VR platforms.
AiSDF: Structure-aware Neural Signed Distance Fields in Indoor Scenes
Indoor scenes we are living in are visually homogenous or textureless, while they inherently have structural forms and provide enough structural priors for 3D scene reconstruction.
Analyzing Downlink Coverage in Clustered Low Earth Orbit Satellite Constellations: A Stochastic Geometry Approach
Our analyses can be used to design reliable satellite cluster networks by effectively estimating the impact of system parameters on the coverage performance.
Hyperbolic Distance-Based Speech Separation
In this work, we explore the task of hierarchical distance-based speech separation defined on a hyperbolic manifold.
Generative De-Quantization for Neural Speech Codec via Latent Diffusion
In low-bitrate speech coding, end-to-end speech coding networks aim to learn compact yet expressive features and a powerful decoder in a single network.
Native Multi-Band Audio Coding within Hyper-Autoencoded Reconstruction Propagation Networks
Spectral sub-bands do not portray the same perceptual relevance.
The Potential of Neural Speech Synthesis-based Data Augmentation for Personalized Speech Enhancement
In the proposed method, we show that the quality of the NSS system's synthetic data matters, and if they are good enough the augmented dataset can be used to improve the PSE system that outperforms the speaker-agnostic baseline.
Neural Feature Predictor and Discriminative Residual Coding for Low-Bitrate Speech Coding
Low and ultra-low-bitrate neural speech coding achieves unprecedented coding gain by generating speech signals from compact speech features.
Upmixing via style transfer: a variational autoencoder for disentangling spatial images and musical content
In the stereo-to-multichannel upmixing problem for music, one of the main tasks is to set the directionality of the instrument sources in the multichannel rendering results.
SpaIn-Net: Spatially-Informed Stereophonic Music Source Separation
With the recent advancements of data driven approaches using deep neural networks, music source separation has been formulated as an instrument-specific supervised problem.
BLOOM-Net: Blockwise Optimization for Masking Networks Toward Scalable and Efficient Speech Enhancement
In this paper, we present a blockwise optimization method for masking-based networks (BLOOM-Net) for training scalable speech enhancement networks.
Don't Separate, Learn to Remix: End-to-End Neural Remixing with Joint Optimization
In this work, we learn to remix music directly by re-purposing Conv-TasNet, a well-known source separation model, into two neural remixing architectures.
HARP-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding
The assumption is that, in a mirrored autoencoder topology, a decoder layer reconstructs the intermediate feature representation of its corresponding encoder layer.
Zero-Shot Personalized Speech Enhancement through Speaker-Informed Model Selection
To this end, we propose using an ensemble model wherein each specialist module denoises noisy utterances from a distinct partition of training set speakers.
Test-Time Adaptation Toward Personalized Speech Enhancement: Zero-Shot Learning with Knowledge Distillation
In addition, since the compact personalized models can outperform larger general-purpose models, we claim that the proposed method performs model compression with no loss of denoising performance.
Efficient Personalized Speech Enhancement through Self-Supervised Learning
To this end, we pose personalization as either a zero-shot task, in which no additional clean speech of the target speaker is used for training, or a few-shot learning task, in which the goal is to minimize the duration of the clean speech used for transfer learning.
Personalized Speech Enhancement through Self-Supervised Data Augmentation and Purification
Training personalized speech enhancement models is innately a no-shot learning problem due to privacy constraints and limited access to noise-free speech from the target user.
Scalable and Efficient Neural Speech Coding: A Hybrid Design
We formulate the speech coding problem as an autoencoding task, where a convolutional neural network (CNN) performs encoding and decoding as a neural waveform codec (NWC) during its feedforward routine.
Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding
Conventional audio coding technologies commonly leverage human perception of sound, or psychoacoustics, to reduce the bitrate while preserving the perceptual quality of the decoded audio signals.
Self-Supervised Learning from Contrastive Mixtures for Personalized Speech Enhancement
This work explores how self-supervised learning can be universally used to discover speaker-specific features towards enabling personalized speech enhancement models.
Sparse Mixture of Local Experts for Efficient Speech Enhancement
In this paper, we investigate a deep learning approach for speech denoising through an efficient ensemble of specialist neural networks.
Boosted Locality Sensitive Hashing: Discriminative Binary Codes for Source Separation
Speech enhancement tasks have seen significant improvements with the advance of deep learning technology, but with the cost of increased computational complexity.
Deep Autotuner: a Pitch Correcting Network for Singing Performances
We train our neural network model using a dataset of 4, 702 amateur karaoke performances selected for good intonation.
Nearest Neighbor Search-Based Bitwise Source Separation Using Discriminant Winner-Take-All Hashing
We propose an iteration-free source separation algorithm based on Winner-Take-All (WTA) hash codes, which is a faster, yet accurate alternative to a complex machine learning model for single-channel source separation in a resource-constrained environment.
Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation
Our experiments show that the proposed BGRU method produces source separation results greater than that of a real-valued fully connected network, with 11-12 dB mean Signal-to-Distortion Ratio (SDR).
A Dual-Staged Context Aggregation Method Towards Efficient End-To-End Speech Enhancement
In speech enhancement, an end-to-end deep neural network converts a noisy speech signal to a clean speech directly in time domain without time-frequency transformation or mask estimation.
Cascaded Cross-Module Residual Learning towards Lightweight End-to-End Speech Coding
Speech codecs learn compact representations of speech signals to facilitate data transmission.
Performance Optimization on Model Synchronization in Parallel Stochastic Gradient Descent Based SVM
In this research, we identify the bottlenecks in model synchronization in parallel stochastic gradient descent (PSGD)-based SVM algorithm with respect to the training model synchronization frequency (MSF).
AutoQ: Automated Kernel-Wise Neural Network Quantization
Recent network quantization techniques quantize each weight kernel in a convolutional layer independently for higher inference accuracy, since the weight kernels in a layer exhibit different variances and hence have different amounts of redundancy.
Deep Autotuner: A Data-Driven Approach to Natural-Sounding Pitch Correction for Singing Voice in Karaoke Performances
This approach differs from commercially used automatic pitch correction systems, where notes in the vocal tracks are shifted to be centered around notes in a user-defined score or mapped to the closest pitch among the twelve equal-tempered scale degrees.
DeepPicar: A Low-cost Deep Neural Network-based Autonomous Car
We present DeepPicar, a low-cost deep neural network based autonomous car platform.
Other Computer Science Distributed, Parallel, and Cluster Computing Performance
Collaborative Deep Learning for Speech Enhancement: A Run-Time Model Selection Method Using Autoencoders
Therefore, the AE can gauge the quality of the module-specific denoised result by seeing its AE reconstruction error, e. g. low error means that the module output is similar to clean speech.
Bitwise Neural Networks
Based on the assumption that there exists a neural network that efficiently represents a set of Boolean functions between all binary inputs and outputs, we propose a process for developing and deploying neural networks whose weight parameters, bias terms, input, and intermediate hidden layer output signals, are all binary-valued, and require only basic bit logic for the feedforward pass.
Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation
In this paper, we explore joint optimization of masking functions and deep recurrent neural networks for monaural source separation tasks, including monaural speech separation, monaural singing voice separation, and speech denoising.
Deep learning for monaural speech separation
In this paper, we study deep learning for monaural speech separation.
