Search Results for author:
Found 23 papers, 14 papers with code
Complete and separate: Conditional separation with missing target source attribute completion
Recent approaches in source separation leverage semantic information about their input mixtures and constituent sources that when used in conditional separation models can achieve impressive performance.
Latent Iterative Refinement for Modular Source Separation
During inference, we can dynamically adjust how many processing blocks and iterations of a specific block an input signal needs using a gating module.
Optimal Condition Training for Target Source Separation
Recent research has shown remarkable performance in leveraging multiple extraneous conditional and non-mutually exclusive semantic concepts for sound source separation, allowing the flexibility to extract a given target source based on multiple different queries.
AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation
We identify several limitations of previous work on audio-visual on-screen sound separation, including the coarse resolution of spatio-temporal attention, poor convergence of the audio separation model, limited variety in training and evaluation data, and failure to account for the trade off between preservation of on-screen sounds and suppression of off-screen sounds.
Learning Representations for New Sound Classes With Continual Self-Supervised Learning
In this paper, we work on a sound recognition system that continually incorporates new sound classes.
Heterogeneous Target Speech Separation
We introduce a new paradigm for single-channel target source separation where the sources of interest can be distinguished using non-mutually exclusive concepts (e. g., loudness, gender, language, spatial location, etc).
RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing
RemixIT is based on a continuous self-training scheme in which a pre-trained teacher model on out-of-domain data infers estimated pseudo-target signals for in-domain mixtures.
Continual self-training with bootstrapped remixing for speech enhancement
Specifically, a separation teacher model is pre-trained on an out-of-domain dataset and is used to infer estimated target signals for a batch of in-domain mixtures.
Improving On-Screen Sound Separation for Open-Domain Videos with Audio-Visual Self-Attention
We introduce a state-of-the-art audio-visual on-screen sound separation system which is capable of learning to separate sounds and associate them with on-screen objects by looking at in-the-wild videos.
Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data
We propose FEDENHANCE, an unsupervised federated learning (FL) approach for speech enhancement and separation with non-IID distributed data across multiple clients.
Unsupervised low-rank representations for speech emotion recognition
We examine the use of linear and non-linear dimensionality reduction algorithms for extracting low-rank feature representations for speech emotion recognition.
Compute and memory efficient universal sound source separation
Recent progress in audio source separation lead by deep learning has enabled many neural network models to provide robust solutions to this fundamental estimation problem.
Ranked #5 on
Speech Separation
on WHAMR!
Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds
For evaluation and semi-supervised experiments, we collected human labels for presence of on-screen and off-screen sounds on a small subset of clips.
Unified Gradient Reweighting for Model Biasing with Applications to Source Separation
In this paper, we propose a simple, unified gradient reweighting scheme, with a lightweight modification to bias the learning process of a model and steer it towards a certain distribution of results.
Sudo rm -rf: Efficient Networks for Universal Audio Source Separation
In this paper, we present an efficient neural network for end-to-end general purpose audio source separation.
Ranked #11 on
Speech Separation
on WHAMR!
Unsupervised Sound Separation Using Mixture Invariant Training
In such supervised approaches, a model is trained to predict the component sources from synthetic mixtures created by adding up isolated ground-truth sources.
Improving Universal Sound Separation Using Sound Classification
Deep learning approaches have recently achieved impressive performance on both audio source separation and sound classification.
Two-Step Sound Source Separation: Training on Learned Latent Targets
In the first step we learn a transform (and it's inverse) to a latent space where masking-based separation performance using oracles is optimal.
Ranked #26 on
Speech Separation
on WSJ0-2mix
Continual Learning of New Sound Classes using Generative Replay
We show that by incrementally refining a classifier with generative replay a generator that is 4% of the size of all previous training data matches the performance of refining the classifier keeping 20% of all previous training data.
Bootstrapped Coordinate Search for Multidimensional Scaling
The backbone element of CSMDS framework is the corresponding probability matrix that correspond to how likely is each corresponding coordinate to be evaluated.
Integrating Recurrence Dynamics for Speech Emotion Recognition
We investigate the performance of features that can capture nonlinear recurrence dynamics embedded in the speech signal for the task of Speech Emotion Recognition (SER).
Ranked #49 on
Emotion Recognition in Conversation
on IEMOCAP
Emotion Recognition in Conversation
Speech Emotion Recognition
Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information
We present a monophonic source separation system that is trained by only observing mixtures with no ground truth separation information.
Pattern Search Multidimensional Scaling
We present a novel view of nonlinear manifold learning using derivative-free optimization techniques.
