DocumentCode
1764996
Title
Time-Frequency Analysis as Probabilistic Inference
Author
Turner, Richard E. ; Sahani, Maneesh
Author_Institution
Dept. of Eng., Univ. of Cambridge, Cambridge, UK
Volume
62
Issue
23
fYear
2014
fDate
Dec.1, 2014
Firstpage
6171
Lastpage
6183
Abstract
This paper proposes a new view of time-frequency analysis framed in terms of probabilistic inference. Natural signals are assumed to be formed by the superposition of distinct time-frequency components, with the analytic goal being to infer these components by application of Bayes´ rule. The framework serves to unify various existing models for natural time-series; it relates to both the Wiener and Kalman filters, and with suitable assumptions yields inferential interpretations of the short-time Fourier transform, spectrogram, filter bank, and wavelet representations. Value is gained by placing time-frequency analysis on the same probabilistic basis as is often employed in applications such as denoising, source separation, or recognition. Uncertainty in the time-frequency representation can be propagated correctly to application-specific stages, improving the handing of noise and missing data. Probabilistic learning allows modules to be co-adapted; thus, the time-frequency representation can be adapted to both the demands of the application and the time-varying statistics of the signal at hand. Similarly, the application module can be adapted to fine properties of the signal propagated by the initial time-frequency processing. We demonstrate these benefits by combining probabilistic time-frequency representations with non-negative matrix factorization, finding benefits in audio denoising and inpainting tasks, albeit with higher computational cost than incurred by the standard approach.
Keywords
Bayes methods; Fourier transforms; Kalman filters; Wiener filters; channel bank filters; matrix decomposition; source separation; time-frequency analysis; Bayes rule; Kalman filters; Wiener filters; computational cost; filter bank; natural signals; natural time-series; nonnegative matrix factorization; probabilistic inference; probabilistic learning; short-time Fourier transform; source separation; time-frequency analysis; time-varying statistics; wavelet representations; Hidden Markov models; Noise; Noise reduction; Probabilistic logic; Spectrogram; Time-frequency analysis; Uncertainty; Audio signal processing; inference; machine- learning; time-frequency analysis;
fLanguage
English
Journal_Title
Signal Processing, IEEE Transactions on
Publisher
ieee
ISSN
1053-587X
Type
jour
DOI
10.1109/TSP.2014.2362100
Filename
6918491
Link To Document