A noise-estimation algorithm for highly non-stationary environments

By Sundarrajan Rangachari, P. Loizou. Speech Communication, 2006

407 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computational Mechanics, Signal Processing

View Paper: https://www.semanticscholar.org/paper/6a2468e137cfb4c6eda5e14d8e7da94d330c4b15

How researchers see this paper

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

In Cognitive Neuroscience

1. Aaron Nicolson
2. Kuldip K. Paliwal
3. Deliang Wang
4. Gibak Kim
5. P. Loizou
6. Y. Hu
7. Chin-Hui Lee
8. Richard Christian Hendriks

In Computational Mechanics

1. Deliang Wang
2. Chin-Hui Lee
3. P. Loizou
4. Gibak Kim
5. Y. Hu
6. Kuldip K. Paliwal
7. Jun Du
8. Aaron Nicolson

In Signal Processing

1. Deliang Wang
2. Kuldip K. Paliwal
3. Chin-Hui Lee
4. Gibak Kim
5. Aaron Nicolson
6. Y. Hu
7. Jun Du
8. P. Loizou

Citations in the corpus

• A Regression Approach to Speech Enhancement Based on Deep Neural Networks (2015, methodology): “A simple yet effective method to cope with the unseen noise conditions is to include many different noise types in the training set [15], [27].”
• Unbiased MMSE-Based Noise Power Estimation With Low Complexity and Low Tracking Delay (2012, methodology): “The methods of Sohn and Sung [18], Cohen [16], and Rangachari and Loizou [17] are based on a recursive averaging of the noisy spectral power using the speech presence probability (SPP) which is obtained from the ratio of the likelihood functions of speech presence and speech absence.”
• Subjective comparison and evaluation of speech enhancement algorithms (2007, methodology): “To assess the merit of noise-estimation algorithms, two speechenhancement algorithms (denoted in Table 3 with the suffix -ne) were also implemented with a noise-estimation algorithm (Rangachari and Loizou, 2006).”
• Reasons why current speech-enhancement algorithms do not improve speech intelligibility and suggested solutions (2011, methodology): “Hu and Loizou [2], [4] showed that algorithms that improve speech quality do not improve speech intelligibility.”
• Subjective Comparison of Speech Enhancement Algorithms (2006, methodology): “To assess the merit of noise-estimation algorithms [7], two speech-enhancement algorithms were implemented with both VAD and noise estimation algorithms.”
• DeepMMSE: A Deep Learning Approach to MMSE-Based Noise Power Spectral Density Estimation (2020, methodology): “As in [14], [17], [20], [22], [23], the DD approach is used to estimate the a priori SNR for the MS, MCRA-2, MMSE, SPP, and ImMMSE methods.”