Audio Signal Enhancement with Learning from Positive and Unlabelled Data

by   Nobutaka Ito, et al.

Supervised learning is a mainstream approach to audio signal enhancement (SE) and requires parallel training data consisting of both noisy signals and the corresponding clean signals. Such data can only be synthesised and are thus mismatched with real data, which can result in poor performance. Moreover, it is often difficult/impossible to obtain clean signals, making it difficult/impossible to apply the approach in this case. Here we explore SE using non-parallel training data consisting of noisy signals and noise, which can be easily recorded. We define the positive (P) and the negative (N) classes as signal absence and presence, respectively. We observe that the spectrogram patches of noise clips can be used as P data and those of noisy signal clips as unlabelled data. Thus, learning from positive and unlabelled data enables a convolutional neural network to learn to classify each spectrogram patch as P or N for SE.


EMGSE: Acoustic/EMG Fusion for Multimodal Speech Enhancement

Multimodal learning has been proven to be an effective method to improve...

Speech Enhancement Based on Cyclegan with Noise-informed Training

Speech enhancement (SE) approaches can be classified into supervised and...

Distributed Microphone Speech Enhancement based on Deep Learning

Speech-related applications deliver inferior performance in complex nois...

Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss

Self-supervised learning (SSL) is the latest breakthrough in speech proc...

Motion Artifact Reduction In Photoplethysmography For Reliable Signal Selection

Photoplethysmography (PPG) is a non-invasive and economical technique to...

Audio-Visual Speech Enhancement Using Multimodal Deep Convolutional Neural Networks

Speech enhancement (SE) aims to reduce noise in speech signals. Most SE ...

Data-Driven AI Model Signal-Awareness Enhancement and Introspection

AI modeling for source code understanding tasks has been making signific...

Code Repositories


Audio signal enhancement with learning from positive and unlabelled data.

view repo

Please sign up or login with your details

Forgot password? Click here to reset