A generalized subspace approach for enhancing speech corrupted by colored noise

By Y. Hu, P. Loizou. IEEE Transactions on Speech and Audio Processing, 2003

410 citations recorded by the source corpus.

Subfields: Computational Mechanics, Signal Processing

View Paper: https://www.semanticscholar.org/paper/7dddfada0c1ed2c525bad5ef1b65253d387992cf

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. P. Loizou
2. Y. Hu
3. Jacob Benesty
4. Gibak Kim
5. Jingdong Chen
6. Deliang Wang
7. Shmulik Markovich Golan
8. Yiteng Huang

In Signal Processing

1. Deliang Wang
2. P. Loizou
3. Yu Tsao
4. Y. Hu
5. Gibak Kim
6. Jacob Benesty
7. Sharon Gannot
8. Xugang Lu

Citations in the corpus

• New insights into the noise reduction Wiener filter (2006, methodology): “A variety of approaches have been developed, including Wiener filter [3], [14]–[19], spectral or cepstral restoration [17], [20]–[27], signal subspace [28]–[35], parametric-model-based method [36]–[38], and statistical-model-based method [5], [39]–[46].”
• Reasons why current speech-enhancement algorithms do not improve speech intelligibility and suggested solutions (2011, methodology): “The subspace techniques (e.g., [8]) were designed to minimize a mathematically-derived speech distortion measure, but make no attempt Fig.”
• Subjective comparison and evaluation of speech enhancement algorithms (2007, methodology): “The generalized subspace approach (Hu and Loizou, 2003) performed significantly (p = 0.”
• Speech Enhancement in Multiple-Noise Conditions Using Deep Neural Networks (2016, neutral): “Other popular classical methods include signal-subspace based methods [7] [8].”
• On Optimal Frequency-Domain Multichannel Linear Filtering for Noise Reduction (2010, background): “Reference [7] provides a good survey on time-domain multichannel beamforming algorithms for acoustic signals.”
• Multichannel Eigenspace Beamforming in a Reverberant Noisy Environment With Multiple Interfering Speech Signals (2009, methodology): “Hu and Loizou [23] extended this method to deal with the colored noise case by using the GEVD rather than the EVD as in the white noise case.”
• SNR-Aware Convolutional Neural Network Modeling for Speech Enhancement (2016, background): “Successful examples include spectral subtraction [1], minimum-mean square error (MMSE) based spectral amplitude estimator [2], Wiener filtering [3], Karhunen-Loéve transformation (KLT) [4], and non-negative matrix factorization (NMF) [5].”