DCCRN+: Channel-Wise Subband DCCRN with SNR Estimation for Speech Enhancement

Lv, Shubo; Hu, Yi; Zhang, Shimin; Xie, Lei

doi:10.21437/interspeech.2021-1482

Cited by 48 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further modification include an introduction of convolutional pathways, with filter kernel of 1 × 1, between the encoder and decoder through skip-connections, which is a similar idea to the DCCRN+ presented in [19]. However, instead of performing concatenation along the feature dimension, we propose to sum the output from the convolution path with the output of the preceding deconvolutional layer, before feeding it to the next deconvolutional layer.…”

Section: Further Modifications To the Network Architecture And Loss F...mentioning

confidence: 99%

Causal Signal-Based DCCRN with Overlapped-Frame Prediction for Online Speech Enhancement

Bartolewska¹,

Kacprzak²,

Kowalczyk³

2023

Interspeech 2023

View full text Add to dashboard Cite

The aim of speech enhancement is to improve speech signal quality and intelligibility from a noisy microphone signal. In many applications, it is crucial to enable processing with small computational complexity and minimal requirements regarding access to future signal samples (look-ahead). This paper presents signal-based causal DCCRN that improves online single-channel speech enhancement by reducing the required look-ahead and the number of network parameters. The proposed modifications include complex filtering of the signal, application of overlapped-frame prediction, causal convolutions and deconvolutions, and modification of the loss function. Results of performed experiments indicate that the proposed model with overlapped signal prediction and additional adjustments, achieves similar or better performance than the original DC-CRN in terms of various speech enhancement metrics, while it reduces the latency and network parameter number by around 30%.

show abstract

Section: Further Modifications To the Network Architecture And Loss F...mentioning

confidence: 99%

Causal Signal-Based DCCRN with Overlapped-Frame Prediction for Online Speech Enhancement

Bartolewska¹,

Kacprzak²,

Kowalczyk³

2023

Interspeech 2023

View full text Add to dashboard Cite

show abstract

“…DNS-MOS is used to do model training and model selection during noise suppression development. DNSMOS is also used for doing ablation studies for noise suppressors [22,23]. DNS-MOS has been quite popular, with over a hundred researchers using it after several months of releasing it.…”

Section: Related Workmentioning

confidence: 99%

DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors

Reddy¹,

Gopal²,

Cutler³

2021

Preprint

View full text Add to dashboard Cite

Human subjective evaluation is the "gold standard" to evaluate speech quality optimized for human perception. Perceptual objective metrics serve as a proxy for subjective scores. We have recently developed a non-intrusive speech quality metric called Deep Noise Suppression Mean Opinion Score (DNSMOS) using the scores from ITU-T Rec. P.808 [1] subjective evaluation. The P.808 scores reflect the overall quality of the audio clip. ITU-T Rec. P.835 [2] subjective evaluation framework gives the standalone quality scores of speech and background noise in addition to the overall quality. In this work, we train an objective metric based on P.835 human ratings that outputs 3 scores: i) speech quality (SIG), ii) background noise quality (BAK), and iii) the overall quality (OVRL) of the audio. The developed metric is highly correlated with human ratings, with a Pearson's Correlation Coefficient (PCC)=0.94 for SIG and PCC=0.98 for BAK and OVRL. This is the first non-intrusive P.835 predictor we are aware of. DNSMOS P.835 is made publicly available as an Azure service.

show abstract

“…In the time-frequency processing domain, besides the amplitude features, the importance of the phase features, with which speech quality improves significantly when the phase features are accurately estimated, has been clarified [20]. Therefore, several studies developed phase-aware enhancement methods [21]- [26], of which the most successful is based on the concept of the complex ideal ratio mask (cIRM) [27]. With the development of complex-valued deep neural networks [28], estimating the cIRM from the complex-valued noisy time-frequency representation [23]- [26] becomes possible.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, several studies developed phase-aware enhancement methods [21]- [26], of which the most successful is based on the concept of the complex ideal ratio mask (cIRM) [27]. With the development of complex-valued deep neural networks [28], estimating the cIRM from the complex-valued noisy time-frequency representation [23]- [26] becomes possible. However, the unbounded property of the cIRM makes it difficult for optimization due to the infinite search space [29].…”

Section: Introductionmentioning

confidence: 99%

Phase-Aware Speech Enhancement With Complex Wiener Filter

Nguyen,

Ho,

Akagi

et al. 2023

IEEE Access

View full text Add to dashboard Cite

In speech enhancement, accurate phase reconstruction can significantly improve speech quality. While phase-aware speech enhancement methods using the complex ideal ratio mask (cIRM) have shown promise, the estimation difficulty of the phase is shared with the real and imaginary parts of the cIRM. The pattern lacking in the imaginary part poses particular difficulties. To address this issue, we proposed a phaseaware speech enhancement method that uses a complex Wiener filter, which delegates the estimation of speech and noise amplitude properties and the phase property to different models, mitigating the issues with the cIRM and improving the effectiveness of neural-network training. Our method uses a speech-variance estimation model with a noise-robust vector-quantized variational autoencoder and a phase corrector that maximizes the scale-invariant signal-to-noise ratio in the time domain. To further improve speech-variance estimation, we propose a loss function that uses a categorical distribution of fundamental frequency (F0) for enhancing the spectral fine structure of estimated speech variance. We evaluated our method on the open dataset released by Valentini et al. to directly compare it with other speech-enhancement methods. Our method achieved a perceptual evaluation of speech quality score of 2.86 and short-time objective intelligibility score of 0.94, better than the state-of-the-art method based on cIRM estimation during the 2020 Deep Noise Challenge. Our comprehensive analysis shows that incorporating the proposed loss function for spectral-fine-structure enhancement improves speech quality, especially when the F0 is low.

show abstract

DCCRN+: Channel-Wise Subband DCCRN with SNR Estimation for Speech Enhancement

Cited by 48 publications

References 28 publications

Causal Signal-Based DCCRN with Overlapped-Frame Prediction for Online Speech Enhancement

Causal Signal-Based DCCRN with Overlapped-Frame Prediction for Online Speech Enhancement

DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors

Phase-Aware Speech Enhancement With Complex Wiener Filter

Contact Info

Product

Resources

About