Heterogeneous Target Speech Separation
- URL: http://arxiv.org/abs/2204.03594v1
- Date: Thu, 7 Apr 2022 17:14:20 GMT
- Title: Heterogeneous Target Speech Separation
- Authors: Efthymios Tzinis, Gordon Wichern, Aswin Subramanian, Paris Smaragdis,
Jonathan Le Roux
- Abstract summary: We introduce a new paradigm for single-channel target source separation where the sources of interest can be distinguished using non-mutually exclusive concepts.
Our proposed heterogeneous separation framework can seamlessly leverage datasets with large distribution shifts.
- Score: 52.05046029743995
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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). Our
proposed heterogeneous separation framework can seamlessly leverage datasets
with large distribution shifts and learn cross-domain representations under a
variety of concepts used as conditioning. Our experiments show that training
separation models with heterogeneous conditions facilitates the generalization
to new concepts with unseen out-of-domain data while also performing
substantially higher than single-domain specialist models. Notably, such
training leads to more robust learning of new harder source separation
discriminative concepts and can yield improvements over permutation invariant
training with oracle source selection. We analyze the intrinsic behavior of
source separation training with heterogeneous metadata and propose ways to
alleviate emerging problems with challenging separation conditions. We release
the collection of preparation recipes for all datasets used to further promote
research towards this challenging task.
Related papers
- Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models [83.02797560769285]
Data-Free Meta-Learning (DFML) aims to derive knowledge from a collection of pre-trained models without accessing their original data.
Current methods often overlook the heterogeneity among pre-trained models, which leads to performance degradation due to task conflicts.
We propose Task Groupings Regularization, a novel approach that benefits from model heterogeneity by grouping and aligning conflicting tasks.
arXiv Detail & Related papers (2024-05-26T13:11:55Z) - Learning Invariant Molecular Representation in Latent Discrete Space [52.13724532622099]
We propose a new framework for learning molecular representations that exhibit invariance and robustness against distribution shifts.
Our model achieves stronger generalization against state-of-the-art baselines in the presence of various distribution shifts.
arXiv Detail & Related papers (2023-10-22T04:06:44Z) - Tackling Computational Heterogeneity in FL: A Few Theoretical Insights [68.8204255655161]
We introduce and analyse a novel aggregation framework that allows for formalizing and tackling computational heterogeneous data.
Proposed aggregation algorithms are extensively analyzed from a theoretical, and an experimental prospective.
arXiv Detail & Related papers (2023-07-12T16:28:21Z) - Optimal Condition Training for Target Source Separation [56.86138859538063]
We propose a new optimal condition training method for single-channel target source separation.
We show that the complementary information carried by the diverse semantic concepts significantly helps to disentangle and isolate sources of interest.
arXiv Detail & Related papers (2022-11-11T00:04:55Z) - When Relation Networks meet GANs: Relation GANs with Triplet Loss [110.7572918636599]
Training stability is still a lingering concern of generative adversarial networks (GANs)
In this paper, we explore a relation network architecture for the discriminator and design a triplet loss which performs better generalization and stability.
Experiments on benchmark datasets show that the proposed relation discriminator and new loss can provide significant improvement on variable vision tasks.
arXiv Detail & Related papers (2020-02-24T11:35:28Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.