All-pole modeling of degraded speech
By J. Lim, A. Oppenheim. 1978
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- SEGAN: Speech Enhancement Generative Adversarial Network (2017, methodology): “Classic speech enhancement methods are spectral subtraction [6], Wiener filtering [7], statistical model-based meth-ods [8], and subspace algorithms [9, 10].”
- A Supervised Learning Approach to Monaural Segregation of Reverberant Speech (2009, methodology): “Various methods have been proposed for monaural speech enhancement or separation, including spectral subtraction [8], Wiener filtering [13,33], minimum mean square error (MMSE) estimation [18], and subspace analysis [19].”
- Improving GANs for Speech Enhancement (2020, background): “3025020 speech enhancement performance have been reported by these deep-learning based methods over more conventional ones [9], [10]–[12].”
- Time-Frequency Masking-Based Speech Enhancement Using Generative Adversarial Network (2018, background): “The results for SEGAN and Wiener filter-based methods are directly taken from the [18], since the same database and evaluation metrics are used in their work.”
- A noise-estimation algorithm for highly non-stationary environments (2006, methodology): “…critical for the performance of speech-enhancement algorithms as it is needed, for instance, to evaluate the Wiener filter in the Wiener algorithms (Lim and Oppenheim, 1978) or to estimate the a priori SNR in the MMSE algorithms (Ephraim and Malah, 1984) or to estimate the noise covariance matrix…”
- GSVD-based optimal filtering for single and multimicrophone speech enhancement (2002, methodology): “Speech enhancement then roughly consists of estimating the speech AR parameters and applying a (noncausal) Wiener filter [1], [2] or Kalman filter [3], [4] to the noisy signal, where the optimal filters are based on the estimated AR parameters.”