Advances in speech and audio processing and coding

Spanias, Andreas

doi:10.1109/iisa.2015.7388064

Cited by 3 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Audio source separation, the process of recovering constituent source signals from a given audio mixture, is a key component in downstream applications such as audio enhancement and music information retrieval [1,2]. Typically formulated as an inverse optimization problem, source separation has been traditionally solved using a broad class of matrix factorization methods [3,4,5], e.g., Independent Component Analysis (ICA) and Principal Component Analysis (PCA).…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Audio Source Separation Using Generative Priors

Narayanaswamy

Thiagarajan

Spanias³

2020

Interspeech 2020

Self Cite

View full text Add to dashboard Cite

State-of-the-art under-determined audio source separation systems rely on supervised end-end training of carefully tailored neural network architectures operating either in the time or the spectral domain. However, these methods are severely challenged in terms of requiring access to expensive source level labeled data and being specific to a given set of sources and the mixing process, which demands complete re-training when those assumptions change. This strongly emphasizes the need for unsupervised methods that can leverage the recent advances in data-driven modeling, and compensate for the lack of labeled data through meaningful priors. To this end, we propose a novel approach for audio source separation based on generative priors trained on individual sources. Through the use of projected gradient descent optimization, our approach simultaneously searches in the source-specific latent spaces to effectively recover the constituent sources. Though the generative priors can be defined in the time domain directly, e.g. WaveGAN, we find that using spectral domain loss functions for our optimization leads to good-quality source estimates. Our empirical studies on standard spoken digit and instrument datasets clearly demonstrate the effectiveness of our approach over classical as well as state-of-the-art unsupervised baselines.

show abstract