Phase retrieval with Bregman divergences and application to audio signal recovery
Pierre-Hugo Vial, Paul Magron, Thomas Oberlin, Cédric Févotte
IEEE Journal of Selected Topics in Signal Processing, Vol. 15, no. 1, pp. 51-64, January 2021
[Paper] [Code]
On this page, we provide several audio excerpts that illustrate the
audio signal recovery experiments presented in the paper. The speech excerpts are
extracted from the TIMIT dataset, and the music snippets are extracted from the FMA dataset.

Speech recovery from exact spectrogram
Original:
Random phase:

Gradient descents
ADMM
GLA-like
Quadratic
Quadratic
GLA
KL (left)
KL (left)
FGLA
KL (right)
IS (left)
GL-ADMM
β=0.5 (right)

Music recovery from exact spectrogram
Original:
Random phase:

Gradient descents
ADMM
GLA-like
Quadratic
Quadratic
GLA
KL (left)
KL (left)
FGLA
KL (right)
IS (left)
GL-ADMM
β=0.5 (right)

Speech recovery from modified spectrogram
Original:

Input SNR: 10 dB
Random phase:

Gradient descents
ADMM
GLA-like
Quadratic
Quadratic
GLA
KL (left)
KL (left)
FGLA
KL (right)
IS (left)
GL-ADMM
β=0.5 (right)

Input SNR: 0 dB
Random phase:

Gradient descents
ADMM
GLA-like
Quadratic
Quadratic
GLA
KL (left)
KL (left)
FGLA
KL (right)
IS (left)
GL-ADMM
β=0.5 (right)

Input SNR: -10 dB
Random phase:

Gradient descents
ADMM
GLA-like
Quadratic
Quadratic
GLA
KL (left)
KL (left)
FGLA
KL (right)
IS (left)
GL-ADMM
β=0.5 (right)

Input SNR: -20 dB
Random phase:

Gradient descents
ADMM
GLA-like
Quadratic
Quadratic
GLA
KL (left)
KL (left)
FGLA
KL (right)
IS (left)
GL-ADMM
β=0.5 (right)