SNR-Aware Convolutional Neural Network Modeling for Speech Enhancement

By Szu-Wei Fu, Yu Tsao, Xugang Lu. 2016

196 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Bo Li
2. Jinyu Li
3. Rohit Prabhavalkar
4. Deliang Wang
5. Tara N. Sainath
6. Yu Tsao
7. Ke Tan
8. Mira Lilleholt Vik

In Signal Processing

1. Bo Li
2. Jinyu Li
3. Yu Tsao
4. Deliang Wang
5. Tara N. Sainath
6. Ke Tan
7. Rohit Prabhavalkar
8. Szu-Wei Fu

Citations in the corpus

• Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition (2017, background): “networks have also been investigated in the literature for enhancement, such as denoising autoencoders [12], convolution networks [13] and recurrent networks [14].”
• Speech Enhancement with a Generative Adversarial Network (2019, methodology): “A range of deep neural nets have later been applied: convolutional neural nets (CNNs) (Hui et al., 2015; Fu et al., 2016; Park and Lee, 2016), recurrent neural nets (RNNs) (Weninger et al.”
• Learning Complex Spectral Mapping with Gated Convolutional Recurrent Networks for Monaural Speech Enhancement (2019, methodology): “In addition, CNNs have also been used for mask estimation and spectral mapping [7], [25], [11], [31].”
• Deep Learning for Audio Signal Processing (2019, background): “Different types of networks have been investigated in the literature for enhancement, such as denoising autoencoders [137], convolutional networks [138] and recurrent networks [139].”
• Bone-conducted speech enhancement using deep denoising autoencoder (2018, background): “, 2017), convolutional neural networks (Fu et al., 2016; Fu et al., 2017), and fully convolutional networks (Fu et al.”
• End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networks (2017, background): “First, they focus only on processing the magnitude spectrogram, such as log-power spectra (LPS) [1], and leave the phase in its original noisy form [1]–[6].”
• Raw waveform-based speech enhancement by fully convolutional networks (2017, methodology): “In addition, to model the local temporal-spectral structures of a spectrogram efficiently, convolutional neural networks (CNN) have also been employed to further improve the SE performance [14, 15].”
• Supervised Speech Separation Based on Deep Learning: An Overview (2017, unknown): “CNNs have also been used for IRM estimation [83] and 773 spectral mapping [46], [136], [138].”