A perceptually-weighted deep neural network for monaural speech enhancement in various background noise conditions

Liu, Qingju; Wang, Wenwu; Jackson, Philip J. B.; Tang, Yan

doi:10.23919/eusipco.2017.8081412

Cited by 30 publications

(30 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, in [18], the estimation of a metric score can be obtained by the discriminator of a generative adversarial network, and the generator then uses the prediction to decide for a gradient direction for optimization. Also, some perceptual weighting rules are proposed in loss functions for neural network training to achieve a better perceptual quality, e.g., high-energy frequency areas are emphasized in the loss functions in [19,20]. However, a perceptual model is not considered in [19] and the loss function proposed in [20] contains an empirical function to balance boosting high energy components and suppressing low energy components.…”

mentioning

confidence: 99%

A Perceptual Weighting Filter Loss for DNN Training In Speech Enhancement

Zhao

Elshamy

Fingscheidt

2019

2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)

View full text Add to dashboard Cite

Single-channel speech enhancement with deep neural networks (DNNs) has shown promising performance and is thus intensively being studied. In this paper, instead of applying the mean squared error (MSE) as the loss function during DNN training for speech enhancement, we design a perceptual weighting filter loss motivated by the weighting filter as it is employed in analysis-by-synthesis speech coding, e.g., in code-excited linear prediction (CELP). The experimental results show that the proposed simple loss function improves the speech enhancement performance compared to a reference DNN with MSE loss in terms of perceptual quality and noise attenuation. The proposed loss function can be advantageously applied to an existing DNN-based speech enhancement system, without modification of the DNN topology for speech enhancement.

show abstract

mentioning

confidence: 99%

A Perceptual Weighting Filter Loss for DNN Training In Speech Enhancement

Zhao

Elshamy

Fingscheidt

2019

2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)

View full text Add to dashboard Cite

show abstract

“…Second, global MSE optimization usually obtains an oversmoothing estimation which omits some important detailed information. To solve these problems, many new criteria, that consider speech perception, have been proposed in most recent years [9][10][11][12]. The first one is to use perceptually weighted MSE functions, which are proposed to weight the loss in different time-frequency (T-F) regions [10,13].…”

Section: Introductionmentioning

confidence: 99%

“…To solve these problems, many new criteria, that consider speech perception, have been proposed in most recent years [9][10][11][12]. The first one is to use perceptually weighted MSE functions, which are proposed to weight the loss in different time-frequency (T-F) regions [10,13]. The second one is to use objective metrics as loss functions, for examples, perceptual evaluation speech quality (PESQ) [14], short-time objective intelligibility (STOI) [15] and scale-invariant speech distortion ratio (SI-SDR) [16] have been adopted as loss functions.…”

Section: Introductionmentioning

confidence: 99%

A Supervised Speech Enhancement Approach with Residual Noise Control for Voice Communication

Peng

Zheng

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

For voice communication, it is important to extract the speech from its noisy version without introducing unnaturally artificial noise. By studying the subband mean-squared error (MSE) of the speech for unsupervised speech enhancement approaches and revealing its relationship with the existing loss function for supervised approaches, this paper derives a generalized loss function, when taking the residual noise control into account, for supervised approaches. Our generalized loss function contains the well-known MSE loss function and many other often-used loss functions as special cases. Compared with traditional loss functions, our generalized loss function is more flexible to make a good trade-off between speech distortion and noise reduction. This is because a group of well-studied noise shaping schemes can be introduced to control residual noise for practical applications. Objective and subjective test results verify the importance of residual noise control for the supervised speech enhancement approach. B. Trade-off Criterion in FullbandThe fullband MSE of the speech and the fullband residual noise can be, respectively, given byandThe loss function without any constraints can be given bywhere (12) is the same as the newly proposed components loss function as given in [17]. The loss function with residual noise control iswhere

show abstract

“…Sound-source enhancement (SSE) is used to recover the target sound from a noisy observed signal. A recent advancement of SSE is the use of a deep neural network (DNN) to estimate a time-frequency (T-F) mask in the short-time Fourier transform (STFT) domain [1][2][3][4][5][6][7]. In early studies, the mean-squared error (MSE) is used as the cost function to train the parameters of DNN [1,8,9] because a gradient of MSE with respect to the parameters can be calculated analytically.…”

Section: Introductionmentioning

confidence: 99%

Data-driven Design of Perfect Reconstruction Filterbank for DNN-based Sound Source Enhancement

Takeuchi

Yatabe

Oikawa

et al. 2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

We propose a data-driven design method of perfect-reconstruction filterbank (PRFB) for sound-source enhancement (SSE) based on deep neural network (DNN). DNNs have been used to estimate a time-frequency (T-F) mask in the short-time Fourier transform (STFT) domain. Their training is more stable when a simple cost function as mean-squared error (MSE) is utilized comparing to some advanced cost such as objective sound quality assessments. However, such a simple cost function inherits strong assumptions on the statistics of the target and/or noise which is often not satisfied, and the mismatch of assumption results in degraded performance. In this paper, we propose to design the frequency scale of PRFB from training data so that the assumption on MSE is satisfied. For designing the frequency scale, the warped filterbank frame (WFBF) is considered as PRFB. The frequency characteristic of learned WFBF was in between STFT and the wavelet transform, and its effectiveness was confirmed by comparison with a standard STFT-based DNN whose input feature is compressed into the mel scale.

show abstract

A perceptually-weighted deep neural network for monaural speech enhancement in various background noise conditions

Cited by 30 publications

References 14 publications

A Perceptual Weighting Filter Loss for DNN Training In Speech Enhancement

A Perceptual Weighting Filter Loss for DNN Training In Speech Enhancement

A Supervised Speech Enhancement Approach with Residual Noise Control for Voice Communication

Data-driven Design of Perfect Reconstruction Filterbank for DNN-based Sound Source Enhancement

Contact Info

Product

Resources

About