Alert button
Picture for Hua Gao

Hua Gao

Alert button

Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model

Jun 01, 2023
Xiaohuai Le, Tong Lei, Li Chen, Yiqing Guo, Chao He, Cheng Chen, Xianjun Xia, Hua Gao, Yijian Xiao, Piao Ding, Shenyi Song, Jing Lu

Figure 1 for Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model
Figure 2 for Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model
Figure 3 for Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model
Figure 4 for Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model

With fewer feature dimensions, filter banks are often used in light-weight full-band speech enhancement models. In order to further enhance the coarse speech in the sub-band domain, it is necessary to apply a post-filtering for harmonic retrieval. The signal processing-based comb filters used in RNNoise and PercepNet have limited performance and may cause speech quality degradation due to inaccurate fundamental frequency estimation. To tackle this problem, we propose a learnable comb filter to enhance harmonics. Based on the sub-band model, we design a DNN-based fundamental frequency estimator to estimate the discrete fundamental frequencies and a comb filter for harmonic enhancement, which are trained via an end-to-end pattern. The experiments show the advantages of our proposed method over PecepNet and DeepFilterNet.

* accepted by Interspeech 2023 
Viaarxiv icon

Are Learned Molecular Representations Ready For Prime Time?

Apr 02, 2019
Kevin Yang, Kyle Swanson, Wengong Jin, Connor Coley, Philipp Eiden, Hua Gao, Angel Guzman-Perez, Timothy Hopper, Brian Kelley, Miriam Mathea, Andrew Palmer, Volker Settels, Tommi Jaakkola, Klavs Jensen, Regina Barzilay

Figure 1 for Are Learned Molecular Representations Ready For Prime Time?
Figure 2 for Are Learned Molecular Representations Ready For Prime Time?
Figure 3 for Are Learned Molecular Representations Ready For Prime Time?
Figure 4 for Are Learned Molecular Representations Ready For Prime Time?

Advancements in neural machinery have led to a wide range of algorithmic solutions for molecular property prediction. Two classes of models in particular have yielded promising results: neural networks applied to computed molecular fingerprints or expert-crafted descriptors, and graph convolutional neural networks that construct a learned molecular representation by operating on the graph structure of the molecule. However, recent literature has yet to clearly determine which of these two methods is superior when generalizing to new chemical space. Furthermore, prior research has rarely examined these new models in industry research settings in comparison to existing employed models. In this paper, we benchmark models extensively on 19 public and 15 proprietary industrial datasets spanning a wide variety of chemical endpoints. In addition, we introduce a graph convolutional model that consistently outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary datasets. Our empirical findings indicate that while approaches based on these representations have yet to reach the level of experimental reproducibility, our proposed model nevertheless offers significant improvements over models currently used in industrial workflows.

Viaarxiv icon

Chemi-net: a graph convolutional network for accurate drug property prediction

Mar 21, 2018
Ke Liu, Xiangyan Sun, Lei Jia, Jun Ma, Haoming Xing, Junqiu Wu, Hua Gao, Yax Sun, Florian Boulnois, Jie Fan

Figure 1 for Chemi-net: a graph convolutional network for accurate drug property prediction
Figure 2 for Chemi-net: a graph convolutional network for accurate drug property prediction
Figure 3 for Chemi-net: a graph convolutional network for accurate drug property prediction
Figure 4 for Chemi-net: a graph convolutional network for accurate drug property prediction

Absorption, distribution, metabolism, and excretion (ADME) studies are critical for drug discovery. Conventionally, these tasks, together with other chemical property predictions, rely on domain-specific feature descriptors, or fingerprints. Following the recent success of neural networks, we developed Chemi-Net, a completely data-driven, domain knowledge-free, deep learning method for ADME property prediction. To compare the relative performance of Chemi-Net with Cubist, one of the popular machine learning programs used by Amgen, a large-scale ADME property prediction study was performed on-site at Amgen. The results showed that our deep neural network method improved current methods by a large margin. We foresee that the significantly increased accuracy of ADME prediction seen with Chemi-Net over Cubist will greatly accelerate drug discovery.

Viaarxiv icon