Post-Filtering Techniques

Simmer, Klaus Uwe; Bitzer, Jöerg; Marro, Claude

doi:10.1007/978-3-662-04619-7_3

Cited by 198 publications

(99 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Under the assumption that the source signal and the noise are uncorrelated, it has been shown in [2,3] that (4) can be further decomposed into a MVDR beamformer followed by a single channel Wiener filter, which operates at the output of the beamformer:…”

Section: Accepted Manuscriptmentioning

confidence: 99%

“…The most common-used criterion for speech enhancement is the mean-square error (MSE), leading to the Multichannel Wiener filter. This optimal multichannel MSE filter has been shown in [2,3] that can be factorized into a Minimum Variance Distortionless Response (MVDR) beamformer, followed by a single channel Wiener postfilter. However, the MSE distortion of the signal estimate is essentially not the optimum criterion for speech enhancement [4,5].…”

Section: Introductionmentioning

confidence: 99%

“…A variety of post-filtering techniques trying to address this issue have been proposed in the literature [7][8][9][10][11][12]. A quite common method for the formulation of the post-filter transfer function is based on the use of the auto-and cross-power spectral densities of the multichannel input signals [2,7,11]. One of the early methods for post-filter estimation is due to Zelinski [7], which was further studied by Marro et al [13].…”

Section: Introductionmentioning

confidence: 99%

“…ACCEPTED MANUSCRIPT (2) The noise signals are gaussian random processes with zero mean and cross-spectral density matrix Φ vv . (3) The source signal is uncorrelated with the noise signals and the Fourier coefficients of each process are independent in different frequencies.…”

mentioning

confidence: 99%

See 3 more Smart Citations

A generalized estimation approach for linear and nonlinear microphone array post-filters

Lefkimmiatis

Maragos

2007

Speech Communication

View full text Add to dashboard Cite

Section: Accepted Manuscriptmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

A generalized estimation approach for linear and nonlinear microphone array post-filters

Lefkimmiatis

Maragos

2007

Speech Communication

View full text Add to dashboard Cite

“…In order to further alleviate the non-correlated noise on different channels, a fequency-domain Zelinski post-filter [20] is applied to the MMI-beamformed speech, which can be estimated bŷ…”

Section: Post-filteringmentioning

confidence: 99%

A Neural Network Based Regression Approach for Recognizing Simultaneous Speech

Liu

Kumatani

Dines

et al.

Machine Learning for Multimodal Interaction

View full text Add to dashboard Cite

Abstract. This paper presents our approach for automatic speech recognition (ASR) of overlapping speech. Our system consists of two principal components: a speech separation component and a feature estmation component. In the speech separation phase, we first estimated the speaker's position, and then the speaker location information is used in a GSC-configured beamformer with a minimum mutual information (MMI) criterion, followed by a Zelinski and binary-masking postfilter, to separate the speech of different speakers. In the feature estimation phase, the neural networks are trained to learn the mapping from the features extracted from the pre-separated speech to those extracted from the close-talking microphone speech signal. The outputs of the neural networks are then used to generate acoustic features, which are subsequently used in acoustic model adaptation and system evaluation. The proposed approach is evaluated through ASR experiments on the PASCAL Speech Separation Challenge II (SSC2) corpus. We demonstrate that our system provides large improvements in recognition accuracy compared with a single distant microphone case and the performance of ASR system can be significantly improved both through the use of MMI beamforming and feature mapping approaches.

show abstract