Dynamic Gated Recurrent Neural Network for Compute-efficient Speech Enhancement

• URL: http://arxiv.org/abs/2408.12425v2
• Date: Tue, 24 Sep 2024 09:55:47 GMT
• Title: Dynamic Gated Recurrent Neural Network for Compute-efficient Speech Enhancement
• Authors: Longbiao Cheng, Ashutosh Pandey, Buye Xu, Tobi Delbruck, Shih-Chii Liu,
• Abstract summary: We introduce a new Dynamic Gated Recurrent Neural Network (DG-RNN) for compute-efficient speech enhancement models running on resource-constrained platforms. As a realization of the DG-RNN, we propose the Dynamic Gated Recurrent Unit (D-GRU) which does not require additional parameters. Test results obtained from several state-of-the-art compute-efficient RNN-based speech enhancement architectures using the DNS challenge dataset, show that the D-GRU based model variants maintain similar speech intelligibility and quality metrics comparable to the baseline GRU based models.
• Score: 17.702946837323026
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces a new Dynamic Gated Recurrent Neural Network (DG-RNN) for compute-efficient speech enhancement models running on resource-constrained hardware platforms. It leverages the slow evolution characteristic of RNN hidden states over steps, and updates only a selected set of neurons at each step by adding a newly proposed select gate to the RNN model. This select gate allows the computation cost of the conventional RNN to be reduced during network inference. As a realization of the DG-RNN, we further propose the Dynamic Gated Recurrent Unit (D-GRU) which does not require additional parameters. Test results obtained from several state-of-the-art compute-efficient RNN-based speech enhancement architectures using the DNS challenge dataset, show that the D-GRU based model variants maintain similar speech intelligibility and quality metrics comparable to the baseline GRU based models even with an average 50% reduction in GRU computes.

Related papers

• IRNN: Innovation-driven Recurrent Neural Network for Time-Series Data Modeling and Prediction [22.332696262170284]
  We propose Innovation-driven RNN (IRNN), a novel RNN architecture tailored to time-series data modeling and prediction tasks.<n>By adapting the concept of "innovation" from KF to RNN, past prediction errors are adopted as additional input signals to update hidden states of RNN.<n>Experiments on real-world benchmark datasets show that the integration of innovations into various forms of RNN leads to remarkably improved prediction accuracy of IRNN.
  arXiv  Detail & Related papers  (2025-05-09T09:43:40Z)
• Deep-Unrolling Multidimensional Harmonic Retrieval Algorithms on Neuromorphic Hardware [78.17783007774295]
  This paper explores the potential of conversion-based neuromorphic algorithms for highly accurate and energy-efficient single-snapshot multidimensional harmonic retrieval. A novel method for converting the complex-valued convolutional layers and activations into spiking neural networks (SNNs) is developed. The converted SNNs achieve almost five-fold power efficiency at moderate performance loss compared to the original CNNs.
  arXiv  Detail & Related papers  (2024-12-05T09:41:33Z)
• Tiny Graph Neural Networks for Radio Resource Management [4.051523221722475]
  We present the Low Rank Message Passing Graph Neural Network (LR-MPGNN) for radio resource management. The cornerstone of LR-MPGNN is the implementation of a low-rank approximation technique that substitutes the conventional linear layers with their low-rank counterparts. We evaluate the performance of the proposed LR-MPGNN model based on several key metrics.
  arXiv  Detail & Related papers  (2024-03-28T04:35:27Z)
• GNN-Ensemble: Towards Random Decision Graph Neural Networks [3.7620848582312405]
  Graph Neural Networks (GNNs) have enjoyed wide spread applications in graph-structured data. GNNs are required to learn latent patterns from a limited amount of training data to perform inferences on a vast amount of test data. In this paper, we push one step forward on the ensemble learning of GNNs with improved accuracy, robustness, and adversarial attacks.
  arXiv  Detail & Related papers  (2023-03-20T18:24:01Z)
• Learning Power Control for Cellular Systems with Heterogeneous Graph Neural Network [37.060397377445504]
  We show that the power control policy has a combination of different PI and PE properties, and existing HetGNN does not satisfy these properties. We design a parameter sharing scheme for HetGNN such that the learned relationship satisfies the desired properties.
  arXiv  Detail & Related papers  (2020-11-06T02:41:38Z)
• The Surprising Power of Graph Neural Networks with Random Node Initialization [54.4101931234922]
  Graph neural networks (GNNs) are effective models for representation learning on relational data. Standard GNNs are limited in their expressive power, as they cannot distinguish beyond the capability of the Weisfeiler-Leman graph isomorphism. In this work, we analyze the expressive power of GNNs with random node (RNI) We prove that these models are universal, a first such result for GNNs not relying on computationally demanding higher-order properties.
  arXiv  Detail & Related papers  (2020-10-02T19:53:05Z)
• Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies [15.2292571922932]
  We propose a novel architecture for recurrent neural networks. Our proposed RNN is based on a time-discretization of a system of second-order ordinary differential equations. Experiments show that the proposed RNN is comparable in performance to the state of the art on a variety of benchmarks.
  arXiv  Detail & Related papers  (2020-10-02T12:35:04Z)
• Recurrent Graph Tensor Networks: A Low-Complexity Framework for Modelling High-Dimensional Multi-Way Sequence [24.594587557319837]
  We develop a graph filter framework for approximating the modelling of hidden states in Recurrent Neural Networks (RNNs) The proposed framework is validated through several multi-way sequence modelling tasks and benchmarked against traditional RNNs. We show that the proposed RGTN is capable of not only out-performing standard RNNs, but also mitigating the Curse of Dimensionality associated with traditional RNNs.
  arXiv  Detail & Related papers  (2020-09-18T10:13:36Z)
• Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks [61.76338096980383]
  A range of neural architecture search (NAS) techniques are used to automatically learn two types of hyper- parameters of state-of-the-art factored time delay neural networks (TDNNs) These include the DARTS method integrating architecture selection with lattice-free MMI (LF-MMI) TDNN training. Experiments conducted on a 300-hour Switchboard corpus suggest the auto-configured systems consistently outperform the baseline LF-MMI TDNN systems.
  arXiv  Detail & Related papers  (2020-07-17T08:32:11Z)
• Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks [54.27962244835622]
  This paper proposes a new mean-field framework for over- parameterized deep neural networks (DNNs) In this framework, a DNN is represented by probability measures and functions over its features in the continuous limit. We illustrate the framework via the standard DNN and the Residual Network (Res-Net) architectures.
  arXiv  Detail & Related papers  (2020-07-03T01:37:16Z)
• Policy-GNN: Aggregation Optimization for Graph Neural Networks [60.50932472042379]
  Graph neural networks (GNNs) aim to model the local graph structures and capture the hierarchical patterns by aggregating the information from neighbors. It is a challenging task to develop an effective aggregation strategy for each node, given complex graphs and sparse features. We propose Policy-GNN, a meta-policy framework that models the sampling procedure and message passing of GNNs into a combined learning process.
  arXiv  Detail & Related papers  (2020-06-26T17:03:06Z)
• Resource Allocation via Graph Neural Networks in Free Space Optical Fronthaul Networks [119.81868223344173]
  This paper investigates the optimal resource allocation in free space optical (FSO) fronthaul networks. We consider the graph neural network (GNN) for the policy parameterization to exploit the FSO network structure. The primal-dual learning algorithm is developed to train the GNN in a model-free manner, where the knowledge of system models is not required.
  arXiv  Detail & Related papers  (2020-06-26T14:20:48Z)
• Binarized Graph Neural Network [65.20589262811677]
  We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters. Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches. Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
  arXiv  Detail & Related papers  (2020-04-19T09:43:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.