Temporal smoothing of spectral masks in the cepstral domain for speech separation

Madhu, Nilesh; Breithaupt, Colin; Martin, Rainer

doi:10.1109/icassp.2008.4517542

Cited by 34 publications

(39 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For parameter estimation stage, Wiener filter has been extensively used as the gain function in different domain representation for speech signal, as some examples, the short-time Fourier transformation (STFT) [1,2], log STFT [3], Karhunen Loeve transform [4], autoregressive modeling [5,6], cepstral [7] and The work of Pejman mowlaee was partially funded by the European project DIRHA (FP7-ICT-2011-7-288121), by ASD (Acoustic Sensing & Design) and Speech Processing Solutions GmbH Vienna. The work of Rahim Saeidi was funded by the European Community's Seventh Framework Programme (FP7 2007-2013 under grant agreement no.…”

Section: Introductionmentioning

confidence: 99%

On phase importance in parameter estimation in single-channel speech enhancement

Mowlaee

Saeidi

2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

In this paper, we study the impact of exploiting the spectral phase information to further improve the speech quality of the single-channel speech enhancement algorithms. In particular, we focus on the two required steps in a typical single-channel speech enhancement system, namely: parameter estimation solved by a minimum mean square error (MMSE) estimator of the speech spectral amplitude, followed by signal reconstruction stage, where the observed noisy phase is often used. For the parameter estimation stage, in contrast to conventional Wiener filter, a new MMSE estimator is derived which takes into account the clean phase information as a prior information. In our experiments, we show that by including the phase information in the two steps, it is possible to improve the perceived signal quality of the enhanced signal significantly with respect to the methods that do not employ the phase information.Index Terms-Single-channel speech enhancement, phase prior, Wiener filter.

show abstract

Section: Introductionmentioning

confidence: 99%

On phase importance in parameter estimation in single-channel speech enhancement

Mowlaee

Saeidi

2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

show abstract

“…However, a typical problem with the binary T-F masking is the introduction of the errors in the estimation of the masks causing fluctuating musical noise [6]. To mitigate this problem, we employ a cepstral smoothing technique [6] as detailed in the next section.…”

Section: Combining Convolutive Ica and Binary Masking For The Segregamentioning

confidence: 99%

“…To overcome this problem, the spectral smoothing in the cepstral domain is applied to the estimated binary mask. Different levels of smoothing are applied to the binary mask across different frequencies which are determined by pitch information estimated directly from the segregated signals, in contrast to the method in [6]. The following sections in this paper present our proposed multistage approach, experimental evaluation results, conclusions and future work.…”

Section: Introductionmentioning

confidence: 99%

“…Essentially, the musical artifacts are reduced according to the speech production machanism which has the advantage of preserving the broadband structure and pitch information of the speech signal [6,7]. Representing the binary masks of equation (7) and (8) in the cepstral domain we have,…”

Section: Cepstral Smoothing Of the Binary Maskmentioning

confidence: 99%

“…This method can effectively address the aforementioned problems associated with the individual methods. However, errors introduced during the estimation of the IBM may give rise to isolated T-F units and hence result in fluctuating artifacts, i.e., the so-called musical noise [6]. To overcome this problem, the spectral smoothing in the cepstral domain is applied to the estimated binary mask.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A multistage approach to blind separation of convolutive speech mixtures

Jan

Wang

2011

Speech Communication

View full text Add to dashboard Cite

In this paper, we propose a novel algorithm for the separation of convolutive speech mixtures using two-microphone recordings, based on the combination of independent component analysis (ICA) and ideal binary mask (IBM), together with a post-filtering process in the cepstral domain. Essentially, the proposed algorithm consists of three steps. First, a constrained convolutive ICA algorithm is applied to separate the source signals from two-microphone recordings. In the second step, we estimate the IBM by comparing the energy of corresponding time-frequency (T-F) units from the separated sources obtained with the convolutive ICA algorithm. The last step is to reduce musical noise caused typically by T-F masking using cepstral smoothing. The performance of the proposed approach is evaluated based on both reverberant mixtures generated using a simulated room model and real recordings. The proposed algorithm offers considerably higher efficiency, together with improved speech quality while producing similar separation performance as compared with a recent approach.

show abstract

A New Sparse Blind Source Separation Method for Determined Linear Convolutive Mixtures in Time-Frequency Domain

Bella

Saylani

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper presents a new Blind Source Separation method for linear convolutive mixtures, which exploits the sparsity of source signals in the time-frequency domain. This method especially brings a solution to the artifacts problem that affects the quality of signals separated by existing time-frequency methods. These artifacts are in fact introduced by a time-frequency masking operation, used by all these methods. Indeed, by focusing on the case of determined mixtures, we show that this problem can be solved with much less restrictive sparsity assumptions than those of existing methods. Test results show the superiority of our new proposed method over existing ones based on time-frequency masking.

show abstract

Temporal smoothing of spectral masks in the cepstral domain for speech separation

Cited by 34 publications

References 11 publications

On phase importance in parameter estimation in single-channel speech enhancement

On phase importance in parameter estimation in single-channel speech enhancement

A multistage approach to blind separation of convolutive speech mixtures

A New Sparse Blind Source Separation Method for Determined Linear Convolutive Mixtures in Time-Frequency Domain

Contact Info

Product

Resources

About