A two-stage algorithm for one-microphone reverberant speech enhancement

By Mingyang Wu, Deliang Wang. 2006

225 citations recorded by the source corpus.

Subfields: Computational Mechanics, Signal Processing

How researchers see this paper

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

In Computational Mechanics

1. Deliang Wang
2. Yuxuan Wang
3. Kun Han
4. Chin-Hui Lee
5. Kehuang Li
6. Bo Wu
7. Minglei Yang
8. Zhaozhang Jin

In Signal Processing

1. Deliang Wang
2. Yuxuan Wang
3. Chin-Hui Lee
4. Kun Han
5. Lei Xie
6. Arun Narayanan
7. Zhaozhang Jin
8. Kehuang Li

Citations in the corpus

• Time-Frequency Masking in the Complex Domain for Speech Dereverberation and Denoising (2017, neutral): “[43] M. Wu and D. Wang, “A two-stage algorithm for one-microphone reverberant speech enhancement,” IEEE Trans.”
• Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition (2018, background): “Single-microphone speech dereverberation has been intensively studied in the signal processing community and a variety of approaches have been proposed [5, 8, 9, 10, 11].”
• Supervised Speech Separation Based on Deep Learning: An Overview (2017, unknown): “As a result, dere- 915 verberation has been actively investigated for a long time [5], 916 [61], [131], [191].”
• Learning Spectral Mapping for Speech Dereverberation and Denoising (2015, methodology): “Wang photograph and biography not available at the time of publication.”
• A Supervised Learning Approach to Monaural Segregation of Reverberant Speech (2009, methodology): “In their system, an inverse filter is first estimated by maximizing the kurtosis of the inverse-filtered linear prediction residual of the reverberant speech from the target location in the absence of interference [21, 57].”
• A Reverberation-Time-Aware Approach to Speech Dereverberation Based on Deep Neural Networks (2017, methodology): “The generalization capabilities of the proposed DNN models are illustrated in Section V. Finally we summarize our findings in Section VI.”
• Reverberant speech recognition combining deep neural networks and deep autoencoders augmented with a phone-class feature (2015, background): “Speech enhancement techniques include deconvolution approaches that tries to reconstruct clean speech by inverse filtering the reverberant speech [1][2][3] and spectral enhancement approaches that estimate and remove the influences of the late reflection [4][5].”