Subband noise estimation for speech enhancement using a perceptual Wiener filter

Lin, Lao-Sheng; Holmes, W.H.; Ambikairajah, Eliathamby

doi:10.1109/icassp.2003.1198721

Cited by 17 publications

(14 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Section 4 describes a further development of the algorithm, including the 28 refinement of the initial estimates and an iterative estimation algorithm for new, improved speech 29 estimates. Experimental studies of the new approach for speech enhancement and as a preprocessor 30 for feature extraction for speech recognition are described in Section 5. Finally, conclusions are 31 presented in Section 6.…”

mentioning

confidence: 99%

“…Based on the longest matched corpus speech segments found at each time t (i.e., (8)), there 30 can be several ways to build the estimates of the underlying speech frames. In this paper, we 31…”

mentioning

confidence: 99%

“…From each g that models the noise-caused gain loss which applies to all speech frequency bands, 30 we further modeled the gain loss in each frequency band caused by the channel distortion, by 31 selecting the channel characteristic h k for each frequency band, in (3) and (5), from the current g 32 (i.e., no channel distortion) to g − 28 dB with a 2-dB resolution, giving fourteen further levels. …”

mentioning

confidence: 99%

See 2 more Smart Citations

An iterative longest matching segment approach to speech enhancement with additive noise and channel distortion

Crookes

2014

Computer Speech & Language

View full text Add to dashboard Cite

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

An iterative longest matching segment approach to speech enhancement with additive noise and channel distortion

Crookes

2014

Computer Speech & Language

View full text Add to dashboard Cite

“…Much work has been done in order to make good estimates of the noise. In [11][12][13], algorithms are presented which are capable of tracking the noise statistics even during voice activity. However, the algorithm still suffers from a large tracking delay, which is minimized using a Bayesian method for noise estimation in [14].…”

Section: Introductionmentioning

confidence: 99%

Noise reduction in the time domain using joint diagonalization

Nørholm¹,

Benesty²,

Jensen³

et al. 2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

A new filter design based on joint diagonalization of the clean speech and noise covariance matrices is proposed. First, an estimate of the noise is found by filtering the observed signal. The filter for this is generated by a weighted sum of the eigenvectors from the joint diagonalization. Second, an estimate of the desired signal is found by subtraction of the noise estimate from the observed signal. The filter can be designed to obtain a desired trade-off between noise reduction and signal distortion, depending on the number of eigenvectors included in the filter design. This is explored through simulations using a speech signal corrupted by car noise, and the results confirm that the output signal-to-noise ratio and speech distortion index both increase when more eigenvectors are included in the filter design.

show abstract

“…Hence there is a need to update the noise spectrum continuously over time and this can be done using noise-estimation algorithms. Several noise-estimation algorithms have been proposed for speech enhancement applications (Malah et al, 1999;Martin, 2001;Cohen, 2002;Cohen, 2003;Doblinger, 1995;Hirsch and Ehrlicher, 1995;Lin et al, 2003;Stahl et al, 2000;Rangachari et al, 2004;Ris and Dupont, 2001). Martin (2001) proposed a method for estimating the noise spectrum based on tracking the minimum of the noisy speech over a finite window.…”

Section: Introductionmentioning

confidence: 99%