Natural gradient works efficiently in learning
Neural Computation
The Modulation Spectrogram: In Pursuit of an Invariant Representation of Speech
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 3 - Volume 3
Fundamental limitation of frequency domain blind source separation for convolutive mixture of speech
ICASSP '01 Proceedings of the Acoustics, Speech, and Signal Processing, 2001. on IEEE International Conference - Volume 05
Independent vector analysis: an extension of ICA to multivariate components
ICA'06 Proceedings of the 6th international conference on Independent Component Analysis and Blind Signal Separation
ICA'06 Proceedings of the 6th international conference on Independent Component Analysis and Blind Signal Separation
EURASIP Journal on Audio, Speech, and Music Processing - Special issue on environmental sound synthesis, processing, and retrieval
Hi-index | 0.00 |
For short-time Fourier Transform (STFT) domain ICA, dealing with reverberant sounds is a significant issue. It often invites a dilemma on STFT frame length: frames shorter than reverberation time (short frames) generate incomplete instantaneous mixtures, while too long frames may disturb the separation. To improve the separation of such reverberant sounds, the authors propose a new framework which accounts for STFT with short frames. In this framework, time domain convolutive mixtures are transformed to STFT domain convolutive mixtures. For separating the mixtures, an approach of applying another STFT is presented so as to treat them as instantaneous mixtures. The authors experimentally confirmed that this framework outperforms the conventional STFT domain ICA.