Low-Delay Speech Enhancement Using Perceptually Motivated Target and Loss

Zhang, Xu; Ren, Xinlei; Zheng, Xiguang; Chen, Lianwu; Zhang, Chen; Guo, Liang; Yu, Bing

doi:10.21437/interspeech.2021-1410

Cited by 9 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CRN was first introduced to speech enhancement by [56,57]. It nested a recurrent neural network (RNN) module inside the CNN-based encoder-decoder structure [58]. The RNN module is capable of handling long-term contexts in a sequencebased manner [59], but often requires high-level features.…”

Section: Structure Of Dvenmentioning

confidence: 99%

“…The CNN module is able to extract high-level features but mainly focuses on local temporal-spectral patterns [60]. Combining their advantages, the CRN structure has been shown to be very effective for speech enhancement [58,[61][62][63]. Motivated by [58,61], we determined three convolution layers for the encoder, three transposed convolution layers for the decoder, and two LSTM layers between them.…”

Section: Structure Of Dvenmentioning

confidence: 99%

“…Combining their advantages, the CRN structure has been shown to be very effective for speech enhancement [58,[61][62][63]. Motivated by [58,61], we determined three convolution layers for the encoder, three transposed convolution layers for the decoder, and two LSTM layers between them. A skip connection connects the output of each encoder layer to the input of the corresponding decoder layer.…”

Section: Structure Of Dvenmentioning

confidence: 99%

See 2 more Smart Citations

Enhancement of Boring Vibrations Based on Cascaded Dual-Domain Features Extraction for Insect Pest Agrilus planipennis Monitoring

Shi

Chen

Zhang

et al. 2023

Forests

View full text Add to dashboard Cite

Wood-boring beetles are among the most destructive forest pests. The larvae of some species live in the trunks and are covered by bark, rendering them difficult to detect. Early detection of these larvae is critical to their effective management. A promising surveillance method is inspecting the vibrations induced by larval activity in the trunk to identify whether it is infected. As convenient as it seems, it has a significant drawback. The identification process is easily disrupted by environmental noise and results in low accuracy. Previous studies have proven the feasibility and necessity of adding an enhancement procedure before identification. To this end, we proposed a small yet powerful boring vibration enhancement network based on deep learning. Our approach combines frequency-domain and time-domain enhancement in a stacked network. The dataset employed in our study comprises the boring vibrations of Agrilus planipennis larvae and various environmental noises. After enhancement, the SNR (signal-to-noise ratio) increment of a boring vibration segment reaches 18.73 dB, and our model takes only 0.46 s to enhance a 5 s segment on a laptop CPU. The accuracy of several well-known classification models showed a substantial increase using clips enhanced by our model. All experimental results proved our contribution to the early detection of larvae.

show abstract

Section: Structure Of Dvenmentioning

confidence: 99%

Section: Structure Of Dvenmentioning

confidence: 99%

Section: Structure Of Dvenmentioning

confidence: 99%

See 1 more Smart Citation

Enhancement of Boring Vibrations Based on Cascaded Dual-Domain Features Extraction for Insect Pest Agrilus planipennis Monitoring

Shi

Chen

Zhang

et al. 2023

Forests

View full text Add to dashboard Cite

show abstract

“…Most of the studies (i.e. [11]- [21]) provided short-time objective intelligibility (STOI [22], [23]) scores, while a few (i.e. [16], [24], [25]) presented extended STOI (ESTOI [26]) scores.…”

Section: Introductionmentioning

confidence: 99%

On the Predictive Power of Objective Intelligibility Metrics for the Subjective Performance of Deep Complex Convolutional Recurrent Speech Enhancement Networks

Gelderblom,

Tronstad,

Svendsen

et al. 2024

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Speech enhancement (SE) systems aim to improve the quality and intelligibility of degraded speech signals obtained from far-field microphones. Subjective evaluation of the intelligibility performance of these SE systems is uncommon. Instead, objective intelligibility measures (OIMs) are generally used to predict subjective performance increases. Many recent deep learning (DL) based SE systems, are expected to improve the intelligibility of degraded speech as measured by OIMs.However, validation of the ability of these OIMs to predict subjective intelligibility when enhancing a speech signal using DL-based systems is lacking. Therefore, in this study, we evaluate the predictive performance of five popular OIMs. We compare the metrics' predictions with subjective results. For this purpose, we recruited 50 human listeners, and subjectively tested both single channel and multi-channel Deep Complex Convolutional Recurrent Network (DCCRN) based speech enhancement systems.We found that none of the OIMs gave reliable predictions, and that all OIMs overestimated the intelligibility of 'enhanced' speech signals.

show abstract

“…Most of the studies (i.e. [8]- [18]) provided short-time objective intelligibility (STOI [19], [20]) scores, while a few (i.e. [13], [21], [22]) presented extended STOI (ESTOI [23]) scores.…”

Section: Introductionmentioning

confidence: 99%

On the Predictive Power of Objective Intelligibility Metrics for the Subjective Performance of Deep Complex Convolutional Recurrent Speech Enhancement Networks

Gelderblom¹,

Tronstad²,

Svendsen³

et al. 2022

Preprint

View full text Add to dashboard Cite

<div>Speech enhancement (SE) systems aim to improve the quality and intelligibility of degraded speech signals obtained from far-field microphones. Subjective evaluation of the intelligibility performance of these SE systems is uncommon. Instead, objective intelligibility measures (OIMs) are generally used to predict subjective performance increases. Many recent deep learning based SE systems, are expected to improve the intelligibility of degraded speech as measured by OIMs. </div><div><br></div><div>However, validation of the OIMs for this purpose is lacking. Therefore, in this study, we evaluate the predictive performance of five popular OIMs. We compare the metrics' predictions with subjective results. For this purpose, we recruited 50 human listeners, and subjectively tested both single channel and multi-channel Deep Complex Convolutional Recurrent Network (DCCRN) based speech systems. </div><div><br></div><div>We find that none of the OIMs gave reliable predictions, and that all OIMs overestimated the intelligibility of `enhanced' speech signals. </div>

show abstract

Low-Delay Speech Enhancement Using Perceptually Motivated Target and Loss

Cited by 9 publications

References 16 publications

Enhancement of Boring Vibrations Based on Cascaded Dual-Domain Features Extraction for Insect Pest Agrilus planipennis Monitoring

Enhancement of Boring Vibrations Based on Cascaded Dual-Domain Features Extraction for Insect Pest Agrilus planipennis Monitoring

On the Predictive Power of Objective Intelligibility Metrics for the Subjective Performance of Deep Complex Convolutional Recurrent Speech Enhancement Networks

On the Predictive Power of Objective Intelligibility Metrics for the Subjective Performance of Deep Complex Convolutional Recurrent Speech Enhancement Networks

Contact Info

Product

Resources

About