Audio Source Separation and Speech Enhancement

Acronyms

AR	autoregressive
ASR	automatic speech recognition
BSS	blind source separation
CASA	computational auditory scene analysis
DDR	direct‐to‐diffuse ratio
DFT	discrete Fourier transform
DNN	deep neural network
DOA	direction of arrival
DRNN	deep recurrent neural network
DRR	direct‐to‐reverberant ratio
DS	delay‐and‐sum
ERB	equivalent rectangular bandwidth
EM	expectation‐maximization
EUC	Euclidean
FD‐ICA	frequency‐domain independent component analysis
FIR	finite impulse response
GCC	generalized cross‐correlation
GCC‐PHAT	generalized cross‐correlation with phase transform
GMM	Gaussian mixture model
GSC	generalized sidelobe canceler
HMM	hidden Markov model
IC	interchannel (or interaural) coherence
ICA	independent component analysis
ILD	interchannel (or interaural) level difference
IPD	interchannel (or interaural) phase difference
ITD	interchannel (or interaural) time difference
IVA	independent vector analysis
IS	Itakura–Saito
KL	Kullback–Leibler
LCMV	linearly constrained minimum variance
LSTM	long short‐term memory
MAP	maximum a posteriori
MFCC	Mel‐frequency cepstral coefficient
ML	maximum likelihood
MM	majorization‐minimization
MMSE	minimum mean square error
MSC	magnitude squared coherence
MSE	mean square error
MVDR	minimum variance distortionless response
MWF	multichannel Wiener filter
NMF	nonnegative matrix factorization
PLCA	probabilistic latent component analysis
RNN	recurrent neural network
RT60	reverberation time
RTF	relative transfer function
SAR	signal‐to‐artifacts ratio
SDR	signal‐to‐distortion ratio
SINR	signal‐to‐interference‐plus‐noise ratio
SIR	signal‐to‐interference ...