Related papers: Finding Strength in Weakness: Learning to Separate…

Universal source separation targets at separating the audio sources of an arbitrary mix, removing the constraint to operate on a specific domain like speech or music. Yet, the potential of universal source separation is limited because most…

Audio source separation is the process of separating a mixture (e.g. a pop band recording) into isolated sounds from individual sources (e.g. just the lead vocals). Deep learning models are the state-of-the-art in source separation, given…

Supervised multi-channel audio source separation requires extracting useful spectral, temporal, and spatial features from the mixed signals. The success of many existing systems is therefore largely dependent on the choice of features used…

State of the art audio source separation models rely on supervised data-driven approaches, which can be expensive in terms of labeling resources. On the other hand, approaches for training these models without any direct supervision are…

We propose a method for the blind separation of sounds of musical instruments in audio signals. We describe the individual tones via a parametric model, training a dictionary to capture the relative amplitudes of the harmonics. The model…

Detecting medical conditions from speech acoustics is fundamentally a weakly-supervised learning problem: a single, often noisy, session-level label must be linked to nuanced patterns within a long, complex audio recording. This task is…

Recently, audio-visual separation approaches have taken advantage of the natural synchronization between the two modalities to boost audio source separation performance. They extracted high-level semantics from visual inputs as the guidance…

Recent progress in deep learning has enabled many advances in sound separation and visual scene understanding. However, extracting sound sources which are apparent in natural videos remains an open problem. In this work, we present…

Self-supervised sound source localization is usually challenged by the modality inconsistency. In recent studies, contrastive learning based strategies have shown promising to establish such a consistent correspondence between audio and…

We present a joint audio-visual model for isolating a single speech signal from a mixture of sounds such as other speakers and background noise. Solving this task using only audio as input is extremely challenging and does not provide an…

Supervised neural network training has led to significant progress on single-channel sound separation. This approach relies on ground truth isolated sources, which precludes scaling to widely available mixture data and limits progress on…

Despite the overwhelming success of deep learning in various speech processing tasks, the problem of separating simultaneous speakers in a mixture remains challenging. Two major difficulties in such systems are the arbitrary source…

Strong labels are a necessity for evaluation of sound event detection methods, but often scarcely available due to the high resources required by the annotation task. We present a method for estimating strong labels using crowdsourced weak…

In this work, we try to answer two questions: Can deeply learned features with discriminative power benefit an ASR system's robustness to acoustic variability? And how to learn them without requiring framewise labelled sequence training…

In the last couple of years, weakly labeled learning has turned out to be an exciting approach for audio event detection. In this work, we introduce webly labeled learning for sound events which aims to remove human supervision altogether…

We propose a novel algorithm for weakly supervised semantic segmentation based on image-level class labels only. In weakly supervised setting, it is commonly observed that trained model overly focuses on discriminative parts rather than the…

Music source separation is focused on extracting distinct sonic elements from composite tracks. Historically, many methods have been grounded in supervised learning, necessitating labeled data, which is occasionally constrained in its…

Supervised object detection and semantic segmentation require object or even pixel level annotations. When there exist image level labels only, it is challenging for weakly supervised algorithms to achieve accurate predictions. The accuracy…

Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end. Therefore, we investigate end-to-end…

Motivated by the desire to generate labels for real-time data we develop a method to estimate the dependency structure and accuracy of weak supervision sources incrementally. Our method first estimates the dependency structure associated…