Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport
Dec 6, 2021
Speakers
Hsin-Yi Lin
Speaker · 0 followers
Huan-Hsin Tseng
Speaker · 0 followers
About
This paper presents a novel discriminator-constrained optimal transport network (DOTN) that enables unsupervised domain adaptation for speech enhancement (SE), which is an essential regression task in speech processing. The DOTN aims to estimate clean references, given noisy speech signals in a testing domain, by exploiting the knowledge available from the training domain. The domain shift between training and testing data has been reported to be an obstacle to learning problems in diverse fields. Although rich literature exists on unsupervised domain adaptation for classification, the methods proposed, especially in regressions, remain scarce and often depend on additional information regarding the input data. The proposed DOTN approach tactically fuses the optimal transport theory from mathematical analysis with generative adversarial frameworks, to help evaluate continuous labels in the target domain. The experimental results on two SE tasks demonstrate that by extending the classical optimal transport formulation, our proposed DOTN outperforms previous adversarial domain adaptation frameworks in a purely unsupervised manner.This paper presents a novel discriminator-constrained optimal transport network (DOTN) that enables unsupervised domain adaptation for speech enhancement (SE), which is an essential regression task in speech processing. The DOTN aims to estimate clean references, given noisy speech signals in a testing domain, by exploiting the knowledge available from the training domain. The domain shift between training and testing data has been reported to be an obstacle to learning problems in diverse field…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Turing Completeness of Bounded-Precision Recurrent Neural Networks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Neural object recognition in machines and brains
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Interaction data are identifiable even across long periods of time
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
A mechanistic multi-area recurrent network model of decision-making
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
An Exact Characterization of the Generalization Error for the Gibbs Algorithm
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%