A perceptual signal subspace approach for speech enhancement in colored noise

Jabloun,; Champagne,

doi:10.1109/icassp.2002.1005803

Cited by 15 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is why the auditory masking thresholds (AMTs) in human auditory functions were further integrated with the above GSVD-based algorithm to establish an improved framework for speech enhancement in this paper [18], referred to as the perceptually constrained GSVD (PCGSVD)-based approach here. Because this PCGSVD-based approach operates in the generalized singular domain, whereas the conventional auditory masking thresholds (AMTs) are well defined in frequency domain, the previously proposed transformation between the frequency domain and the eigen domain [19] is extended to be performed between the frequency domain and the generalized singular domain [18], with which a closed-form solution for the PCGSVD-based speech enhancement approach is obtained. Experimental results based on various objective and subjective tests (e.g., time/frequency domain evaluations, speech recognition accuracies, paired-utterance listening comparison, mean opinion score (MOS) rating, etc.)…”

mentioning

confidence: 99%

A Perceptually Constrained GSVD-Based Approach for Enhancing Speech Corrupted by Colored Noise

Lee

2007

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

The singular value decomposition (SVD)-based method for single-channel speech enhancement has been shown to be very useful when the additive noise is white. For colored noise, with this approach, one needs to whiten the noise spectrum prior to SVD-based approach and perform the inverse whitening processing afterwards. A truncated quotient SVD (QSVD)-based approach has been proposed to handle this problem and found very useful. In this paper, a generalized SVD (GSVD)-based subspace approach for speech enhancement is first extended from the concept of the truncated QSVD-based approach, in which the dimension of the signal subspace can be precisely and automatically determined for each frame of the noisy signal. But with this new approach some residual noise is still perceivable under lower signal-to-noise ratio conditions. Therefore a perceptually constrained GSVD (PCGSVD)-based approach is further proposed to incorporate the masking properties of human auditory system to make sure the undesired residual noise to be nearly un-perceivable. Closed-form solutions are obtained for both the GSVD-and PCGSVD-based enhancement approaches. Very carefully performed objective evaluations and subjective listening tests show that the PCGSVD-based approach proposed here can offer improved speech quality, intelligibility and recognition accuracy, whether the noise is stationary or nonstationary, especially when the additive noise is nonwhite.

show abstract

mentioning

confidence: 99%

A Perceptually Constrained GSVD-Based Approach for Enhancing Speech Corrupted by Colored Noise

Lee

2007

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…7. Signal subspace [21,22,70,117,120] and singular value decomposition (SVD) [3,58,100] based speech enhancement;…”

Section: Approaches Of Speech Enhancementmentioning

confidence: 99%

“…A typical speech enhancement system [7,10,14,15,21,22,78,79,80] that exploits masking properties is described in Fig. 2.6.…”

Section: The Speech Receiver Modelmentioning

confidence: 99%

“…The masking-based subspace speech enhancement method is reported to yield an improved result over the conventional subspace approaches [21]. It is improved and extended to colored noise in [22]. Nevertheless, the power spectrum solution proposed in [21,22] is a smeared version of the power spectral density (PSD) of the original signal.…”

Section: Introductionmentioning

confidence: 99%

“…It is improved and extended to colored noise in [22]. Nevertheless, the power spectrum solution proposed in [21,22] is a smeared version of the power spectral density (PSD) of the original signal. Subsequently, the inverse equation for eigenvalues is only an approximate solution.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Speech enhancement methods based on masking properties

You¹

View full text Add to dashboard Cite

I would like to express my sincere gratitude to my supervisor, Professor Koh Soo Ngee, and my co-supervisor, Associate Professor Rahardja Susanto, for their invaluable guidance and pertinent advices during my study. Moreover, I would like to thank their constant encouragement, their enormous time and effort that they have made pertaining to this research and thesis writing. I am deeply grateful to my parents, Mr. You Bao Hui and Ms. Zheng Hui Yu, and my wife, Jiang Ping, and my two sons, Li Ming and Li Hong, for their endless love, support and encouragement. I would also like to thank my final year project students from National University of Singapore, Ms. Chen Kexin, Mr. Tan Chun Wee and Ms. Sem Pak Ling, for sharing with me their projects and many interesting and helpful discussions.

show abstract

Frequency domain multi-channel noise reduction based on the spatial subspace decomposition and noise eigenvalue modification

Kim

Cho

2008

Speech Communication

View full text Add to dashboard Cite

A perceptual signal subspace approach for speech enhancement in colored noise

Cited by 15 publications

References 0 publications

A Perceptually Constrained GSVD-Based Approach for Enhancing Speech Corrupted by Colored Noise

A Perceptually Constrained GSVD-Based Approach for Enhancing Speech Corrupted by Colored Noise

Speech enhancement methods based on masking properties

Frequency domain multi-channel noise reduction based on the spatial subspace decomposition and noise eigenvalue modification

Contact Info

Product

Resources

About