相关论文: Interleaved Multitask Learning for Audio Source Se…

In the resource-constrained IoT-edge computing environment, Split Federated (SplitFed) learning is implemented to enhance training efficiency. This method involves each terminal device dividing its full DNN model at a designated layer into…

Radio source detection through conventional algorithms has been unreliable when trying to solve for large number of sources in the presence of low SINR and less number of snapshots. We address this by reformulating source detection as a…

Efficient compression of correlated data is essential to minimize communication overload in multi-sensor networks. In such networks, each sensor independently compresses the data and transmits them to a central node due to limited…

Can we perform an end-to-end music source separation with a variable number of sources using a deep learning model? We present an extension of the Wave-U-Net model which allows end-to-end monaural source separation with a non-fixed number…

Large amount of data is often required to train and deploy useful machine learning models in industry. Smaller enterprises do not have the luxury of accessing enough data for machine learning, For privacy sensitive fields such as banking,…

Dual encoding models that encode a pair of inputs are widely used for representation learning. Many approaches train dual encoding models by maximizing agreement between pairs of encodings on centralized training data. However, in many…

The x-vector based deep neural network (DNN) embedding systems have demonstrated effectiveness for text-independent speaker verification. This paper presents a multi-task learning architecture for training the speaker embedding DNN with the…

We introduce two unsupervised source separation methods, which involve self-supervised training from single-channel two-source speech mixtures. Our first method, mixture permutation invariant training (MixPIT), enables learning a neural…

We study multi-task learning for two orthogonal speech technology tasks: speech and speaker recognition. We use wav2vec2 as a base architecture with two task-specific output heads. We experiment with different architectural decisions to mix…

Multi-Source Diffusion Models (MSDM) allow for compositional musical generation tasks: generating a set of coherent sources, creating accompaniments, and performing source separation. Despite their versatility, they require estimating the…

This article introduces a generalized framework for Decentralized Learning formulated as a Multi-Objective Optimization problem, in which both distributed agents and a central coordinator contribute independent, potentially conflicting…

We propose a unified model for three inter-related tasks: 1) to \textit{separate} individual sound sources from a mixed music audio, 2) to \textit{transcribe} each sound source to MIDI notes, and 3) to\textit{ synthesize} new pieces based…

Several results in the computer vision literature have shown the potential of randomly weighted neural networks. While they perform fairly well as feature extractors for discriminative tasks, a positive correlation exists between their…

Universal sound separation aims to extract clean audio tracks corresponding to distinct events from mixed audio, which is critical for artificial auditory perception. However, current methods heavily rely on artificially mixed audio for…

We consider the problem of joint source and channel coding of structured data such as natural language over a noisy channel. The typical approach to this problem in both theory and practice involves performing source coding to first…

Inspired by the recent progress in self-supervised learning for computer vision, in this paper we introduce DeLoRes, a new general-purpose audio representation learning approach. Our main objective is to make our network learn…

In this paper, we propose a latent-variable generative model called mixture of dynamical variational autoencoders (MixDVAE) to model the dynamics of a system composed of multiple moving sources. A DVAE model is pre-trained on a…

Background noise and room reverberation are regarded as two major factors to degrade the subjective speech quality. In this paper, we propose an integrated framework to address simultaneous denoising and dereverberation under complicated…

Decentralized learning (DL) offers a powerful framework where nodes collaboratively train models without sharing raw data and without the coordination of a central server. In the iterative rounds of DL, models are trained locally, shared…

Federated Learning (FL) has emerged as a prominent privacy-preserving technique for enabling use cases like confidential clinical machine learning. FL operates by aggregating models trained by remote devices which owns the data. Thus, FL…