Auditory-Based Spectral Amplitude Estimators for Speech Enhancement

Plourde, Eric; Champagne, Benoı̂t

doi:10.1109/tasl.2008.2004304

Cited by 47 publications

(37 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Plourde and Champagne in [10] suggested to take advantage of STSA power weightings (as used in the WE estimator) in the β-order MMSE cost function and introduced the parameter α as the power of their new weighting. They further proposed to select the two estimator parameters as functions of frequency, according to the psycho-acoustical properties of the human auditory system and showed a better quality in the enhanced speech in most of the input SNR range.…”

Section: Introductionmentioning

confidence: 99%

Bayesian STSA estimation using masking properties and generalized Gamma prior for speech enhancement

Parchami

Zhu

Champagne

et al. 2015

EURASIP J. Adv. Signal Process.

Self Cite

View full text Add to dashboard Cite

We consider the estimation of the speech short-time spectral amplitude (STSA) using a parametric Bayesian cost function and speech prior distribution. First, new schemes are proposed for the estimation of the cost function parameters, using an initial estimate of the speech STSA along with the noise masking feature of the human auditory system. This information is further employed to derive a new technique for the gain flooring of the STSA estimator. Next, to achieve better compliance with the noisy speech in the estimator’s gain function, we take advantage of the generalized Gamma distribution in order to model the STSA prior and propose an SNR-based scheme for the estimation of its corresponding parameters. It is shown that in Bayesian STSA estimators, the exploitation of a rough STSA estimate in the parameter selection for the cost function and the speech prior leads to more efficient control on the gain function values. Performance evaluation in different noisy scenarios demonstrates the superiority of the proposed methods over the existing parametric STSA estimators in terms of the achieved noise reduction and introduced speech distortion

show abstract

Section: Introductionmentioning

confidence: 99%

Bayesian STSA estimation using masking properties and generalized Gamma prior for speech enhancement

Parchami

Zhu

Champagne

et al. 2015

EURASIP J. Adv. Signal Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Since most of the speech energy is located at the lower frequencies (i.e., larger STSA) and at the higher frequencies, the speech energy is weakened (i.e., smaller STSA) [19], for the lower frequencies, the value of parameter p should be high and vice versa for the higher frequencies. That is, the estimation error at the higher frequencies is penalized more heavily than that at the lower frequencies.…”

Section: Adaptive Calculation Of Parameter Pmentioning

confidence: 99%

Speech enhancement based on Bayesian decision and spectral amplitude estimation

Feng

Bao

2015

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

In this paper, a single-channel speech enhancement method based on Bayesian decision and spectral amplitude estimation is proposed, in which the speech detection module and spectral amplitude estimation module are included, and the two modules are strongly coupled. First, under the decisions of speech presence and speech absence, the optimal speech amplitude estimators are obtained by minimizing a combined Bayesian risk function, respectively. Second, using the obtained spectral amplitude estimators, the optimal speech detector is achieved by further minimizing the combined Bayesian risk function. Finally, according to the detection results of speech detector, the optimal decision rule is made and the optimal spectral amplitude estimator is chosen for enhancing noisy speech. Furthermore, by considering both detection and estimation errors, we propose a combined cost function which incorporates two general weighted distortion measures for the speech presence and speech absence of the spectral amplitudes, respectively. The cost parameters in the cost function are employed to balance the speech distortion and residual noise caused by missed detection and false alarm, respectively. In addition, we propose two adaptive calculation methods for the perceptual weighted order p and the spectral amplitude order β concerned in the proposed cost function, respectively. The objective and subjective test results indicate that the proposed method can achieve a more significant segmental signal-noise ratio (SNR) improvement, a lower log-spectral distortion, and a better speech quality than the reference methods.

show abstract

“…Yet, a few developments of such cost functions have been suggested and used in the literature, such as the auditory based (weighted β-SA) cost function introduced in [4]. Minimization of this parametric Bayesian cost function results in the following STSA estimator…”

Section: B Extension To the Auditory Based Stsa Estimatormentioning

confidence: 99%

“…It should be noted that the frequency dependent parameters α k and β k are to be selected based on the properties of human auditory system, which is elaborated in [4]. Also, the above considered cost function, and hence the resulting estimator, are simplified to the MMSE estimator discussed in Subsection III-A by choosing α k and β k to be zero and one, respectively.…”

Section: B Extension To the Auditory Based Stsa Estimatormentioning

confidence: 99%

“…Several major modifications of their groundbreaking work have been later suggested in the literature, either by defining new perceptually more relevant cost functions, e.g. [4] and references therein, or by taking into account heavytailed non-Gaussian prior distributions in modeling the clean speech STSA [5]. It is noted that the above mentioned STSA estimators are derived by assuming a uniformly distributed speech spectral phase and then treating the problem by taking statistical expectation with respect to this unknown phase.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Microphone array based speech spectral amplitude estimators with phase estimation

Parchami

Zhu

Champagne

2014

2014 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

Bayesian estimators of short time spectral amplitude (STSA) have received considerable attention in the field of speech enhancement. In this paper, we propose new multimicrophone extensions for the conventional Ephraim and Malah's speech spectral amplitude estimation method. Unlike the conventional estimators where the spectral phase is assumed to be uniformly distributed, the proposed extensions treat the latter as an unknown parameter to be estimated. It is shown that the proposed methods can exploit spectral phase estimates to improve the performance of the current speech STSA estimators and have the potential to provide even further improvement given a more accurate estimate of the spectral phase. Experimental results indicate the superiority of the new approaches in terms of noise reduction and speech distortion measures, in addition to the reduced computational complexity provided by the proposed minimum mean square method as compared to state-of-the-art solutions.

show abstract

Auditory-Based Spectral Amplitude Estimators for Speech Enhancement

Cited by 47 publications

References 21 publications

Bayesian STSA estimation using masking properties and generalized Gamma prior for speech enhancement

Bayesian STSA estimation using masking properties and generalized Gamma prior for speech enhancement

Speech enhancement based on Bayesian decision and spectral amplitude estimation

Microphone array based speech spectral amplitude estimators with phase estimation

Contact Info

Product

Resources

About