A Data-Driven Approach to A Priori SNR Estimation

Suhadi, Suhadi; Last, Carsten; Fingscheidt, Tim

doi:10.1109/tasl.2010.2045799

Cited by 66 publications

(32 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The a priori SNR can be estimated by a decision-directed (DD) approach, i.e., a weighted sum of a priori SNR obtained from the previous frame by applying a noise reduction process and the one by a simple variation of a posteriori SNR, namely maximum-likelihood (ML) estimate [18], [22]. denotes the ML estimate of the current frame [23].…”

Section: A Decision-directed (Dd) Approachmentioning

confidence: 99%

See 1 more Smart Citation

A Priori SNR Estimation Using Air- and Bone-Conduction Microphones

Shin

Fingscheidt

Kang

2015

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

This paper proposes an a priori signal-to-noise ratio (SNR) estimator using an air-conduction (AC) and a bone-conduction (BC) microphone. Among various ways of combining AC and BC microphones for speech enhancement, it is shown that the total enhancement performance can be maximized if the BC microphone is utilized for estimating the power spectral density (PSD) of the desired speech signal. Considering the fact that a small deviation in the speech PSD estimation process brings severe spectral distortion, this paper focuses on controlling weighting factors while estimating the a priori SNR with the decision-directed approach framework. The time-frequency varying weighting factor that is determined by taking a minimum mean square error criterion improves the capability of eliminating residual noise and minimizing speech distortion. Since the weighting factors are also adjusted by measuring the usefulness of the AC and BC microphones, the proposed approach is suitable for tracking the parameter even if the characteristic of environment changes rapidly. The simulation results confirm the superiority of the proposed algorithm to conventional algorithms in high noise environments.Index Terms-A priori signal-to-noise ratio (SNR) , bone-conduction (BC) microphone, speech enhancement.

show abstract

Section: A Decision-directed (Dd) Approachmentioning

confidence: 99%

“…(20) for notational convenience. (20) where (21) (22) and . We make full use of the ML-based and the equalized BC-speech-based estimates by adopting the AoU.…”

Section: B Determination Of Weighting Factors By a Utility Measurementioning

confidence: 99%

A Priori SNR Estimation Using Air- and Bone-Conduction Microphones

Shin

Fingscheidt

Kang

2015

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Nevertheless, it cannot provide stable noise suppression and may introduce music noise because the dynamic range of weighting factor is too large. Except the DD approach, many data-driven and acoustic environment classification-based approaches had been proposed [6–8]. In [7], Choi and Chang used Gaussian mixture model (GMM) to identify the type of noise environment and then selected the optimal weighting factor according to the type of noise.…”

Section: Introductionmentioning

confidence: 99%

“…DD can reduce music noise effectively by providing smooth estimation of a priori SNR. However, as analyzed in [6, 9], DD often brings about roughly one-frame delay when it is used to estimate a priori SNR. What is more, the convergence rate of estimation is often slow because the weighting factor is close to 1, and the speech quality may seriously degrade when the delay is large.…”

Section: Introductionmentioning

confidence: 99%

A priori SNR estimation and noise estimation for speech enhancement

Yao

Zeng

Zhu

2016

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

A priori signal-to-noise ratio (SNR) estimation and noise estimation are important for speech enhancement. In this paper, a novel modified decision-directed (DD) a priori SNR estimation approach based on single-frequency entropy, named DDBSE, is proposed. DDBSE replaces the fixed weighting factor in the DD approach with an adaptive one calculated according to change of single-frequency entropy. Simultaneously, a new noise power estimation approach based on unbiased minimum mean square error (MMSE) and voice activity detection (VAD), named UMVAD, is proposed. UMVAD adopts different strategies to estimate noise in order to reduce over-estimation and under-estimation of noise. UMVAD improves the classical statistical model-based VAD by utilizing an adaptive threshold to replace the original fixed one and modifies the unbiased MMSE-based noise estimation approach using an adaptive a priori speech presence probability calculated by entropy instead of the original fixed one. Experimental results show that DDBSE can provide greater noise suppression than DD and UMVAD can improve the accuracy of noise estimation. Compared to existing approaches, speech enhancement based on UMVAD and DDBSE can obtain a better segment SNR score and composite measure covl score, especially in adverse environments such as non-stationary noise and low-SNR.

show abstract

“…The index for the gain is usually found by using signal features provided by a conventional speech enhancement algorithm. More recently, several approaches, instead of deriving the gain directly, estimate the noise power [7] and the a priori signal-to-noise ratio (SNR) [8] in a datadriven manner.…”

Section: Introductionmentioning

confidence: 99%

Speech Enhancement Based on Data-Driven Residual Gain Estimation

Jin

Kim

Chang

2011

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this letter, we propose a novel speech enhancement algorithm based on data-driven residual gain estimation. The entire system consists of two stages. At the first stage, a conventional speech enhancement algorithm enhances the input signal while estimating several signalto-noise ratio (SNR)-related parameters. The residual gain, which is estimated by a data-driven method, is applied to further enhance the signal at the second stage. A number of experimental results show that the proposed speech enhancement algorithm outperforms the conventional speech enhancement technique based on soft decision and the data-driven approach using SNR grid look-up table.

show abstract

A Data-Driven Approach to A Priori SNR Estimation

Cited by 66 publications

References 18 publications

A Priori SNR Estimation Using Air- and Bone-Conduction Microphones

A Priori SNR Estimation Using Air- and Bone-Conduction Microphones

A priori SNR estimation and noise estimation for speech enhancement

Speech Enhancement Based on Data-Driven Residual Gain Estimation

Contact Info

Product

Resources

About