Speech Denoising and Dereverberation Using Probabilistic Models

By Hagai Thomas Attias, John C. Platt, A. Acero, Li Deng. 2000

110 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Adam Polyak
2. Lior Wolf
3. Yossi Adi
4. Yaniv Taigman
5. Yoshua Bengio
6. Xu Tan
7. Wei-Ning Hsu
8. Junichi Yamagishi

Citations in the corpus

• SEANet: A Multi-modal Speech Enhancement Network (2020, neutral): “Traditional signal processing methods adopt spectral noise subtraction [1, 2], spectral masking [3, 4], statistical methods based on Wiener filtering [5] and Bayesian estimators [6, 7].”
• One Microphone Source Separation (2000, background): “Atti as and colleagues [ 9 ] developed a fully probabilistic model of speech in noise and used varia tional Bayesian techniques to perform inference and learning allowing denoising and dereverberation; their approach clearly has the potential to be applied to the separation pro blem as well.”
• High Fidelity Speech Regeneration with Application to Speech Enhancement (2021, background): “Speech enhancement and speech dereverberation were widely explored over the years [1, 2].”
• Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech (2018, background): “There have been some studies that have attempted to remove both noise and reverberation from the speech signal, either by performing noise suppression and dereverberation sequentially or proposing an integrated approach [16]–[21].”