论文信息 - Single-Channel Signal Enhancement in the STFT Domain

Single-Channel Signal Enhancement in the STFT Domain

In this chapter, we study the signal enhancement problem in the convenient short-time Fourier transform (STFT) domain. Contrary to most conventional approaches, we do not assume here that successive STFT frames are uncorrelated. As a consequence, the interframe correlation is now taken into account and a filter is used in each subband instead of just a gain to enhance the noisy signal. We show how to apply some of the concepts of variable span (VS) linear filtering to this problem.

Jacob Benesty | Mads Græsbøll Christensen | Jesper Jensen

[1] Israel Cohen,et al. Speech spectral modeling and enhancement based on autoregressive conditional heteroscedasticity models , 2006, Signal Process..

[2] Israel Cohen,et al. Relaxed statistical model for speech enhancement and a priori SNR estimation , 2005, IEEE Transactions on Speech and Audio Processing.

[3] David Pearce,et al. The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions , 2000, INTERSPEECH.

[4] Israel Cohen,et al. Noise spectrum estimation in adverse environments: improved minima controlled recursive averaging , 2003, IEEE Trans. Speech Audio Process..

[5] Rainer Martin,et al. Noise power spectral density estimation based on optimal smoothing and minimum statistics , 2001, IEEE Trans. Speech Audio Process..

[6] Wonyong Sung,et al. A statistical model-based voice activity detection , 1999, IEEE Signal Processing Letters.

[7] David W. Lewis,et al. Matrix theory , 1991 .

[8] Richard C. Hendriks,et al. Unbiased MMSE-Based Noise Power Estimation With Low Complexity and Low Tracking Delay , 2012, IEEE Transactions on Audio, Speech, and Language Processing.