Subjective Comparison of Speech Enhancement Algorithms

By Y. Hu, P. Loizou. 2006

265 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. Ross Cutler
2. P. Loizou
3. Y. Hu
4. Yossi Adi
5. Junichi Yamagishi
6. Cassia Valentini-Botinhao
7. Qifeng Chen
8. Chandan K. A. Reddy

In Signal Processing

1. Dong Yu
2. Li Deng
3. Jinyu Li
4. Yifan Gong
5. Ross Cutler
6. Deliang Wang
7. Yossi Adi
8. Gabriel Synnaeve

Citations in the corpus

• Speech Denoising with Deep Feature Losses (2018, methodology): “We use here the composite scores from [42] that were found to be best correlated with human listener ratings.”
• Real Time Speech Enhancement in the Waveform Domain (2020, methodology): “Traditionally speech enhancement methods generate either an enhanced version of the magnitude spectrum or produce an estimate of the ideal binary mask (IBM) that is then used to enhance the magnitude spectrum [5, 33].”
• Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech (2016, unknown): “Statistical model-based speech enhancement methods have been shown to generate higher quality speech in subjective evaluations over Wiener, spectral subtractive and subspace algorithms [4].”
• Evaluation of Objective Quality Measures for Speech Enhancement (2008, methodology): “Of these two types of distortion, listeners seem to be influenced the most by the speech distortion when making judgments of overall quality [10], [11].”
• A minimum-mean-square-error noise reduction algorithm on Mel-frequency cepstra for robust speech recognition (2008, background): “Subjective human listening experiments [8] show that speech enhancement becomes more effective when applied to the log-spectral amplitude domain [7].”
• Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech (2018, methodology): “speech than methods such as spectral subtraction, Wiener filter and subspace-based ones [4].”
• Robust Speech Recognition Using a Cepstral Minimum-Mean-Square-Error-Motivated Noise Suppressor (2008, background): “Digital Object Identifier 10.1109/TASL.2008.921761 traditionally applied in the spectral domain (e.g., spectral subtraction, Wiener filtering, and Ephraim/Malah spectral amplitude MMSE suppressor [7], [13]).”
• A scalable noisy speech dataset and online subjective test framework (2019, methodology): “The Noizeus dataset [12] is a widely used narrowband dataset with about 0.”