Related papers: Inference skipping for more efficient real-time sp…

We study large-scale kernel methods for acoustic modeling in speech recognition and compare their performance to deep neural networks (DNNs). We perform experiments on four speech recognition datasets, including the TIMIT and Broadcast News…

Data augmentation is a widely used technique in machine learning to improve model performance. However, existing data augmentation techniques in natural language understanding (NLU) may not fully capture the complexity of natural language…

We apply a fast kernel method for mask-based single-channel speech enhancement. Specifically, our method solves a kernel regression problem associated to a non-smooth kernel function (exponential power kernel) with a highly efficient…

Subjective evaluation results for two low-latency deep neural networks (DNN) are compared to a matured version of a traditional Wiener-filter based noise suppressor. The target use-case is real-world single-channel speech enhancement…

Recurrent Neural Networks (RNNs) are useful in temporal sequence tasks. However, training RNNs involves dense matrix multiplications which require hardware that can support a large number of arithmetic operations and memory accesses.…

Spiking Neural Network (SNN) is a promising energy-efficient AI model when implemented on neuromorphic hardware. However, it is a challenge to efficiently train SNNs due to their non-differentiability. Most existing methods either suffer…

In speech enhancement, an end-to-end deep neural network converts a noisy speech signal to a clean speech directly in time domain without time-frequency transformation or mask estimation. However, aggregating contextual information from a…

The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory…

We study the role of magnitude structured pruning as an architecture search to speed up the inference time of a deep noise suppression (DNS) model. While deep learning approaches have been remarkably successful in enhancing audio quality,…

Speaker diarization is an important pre-processing step for many speech applications, and it aims to solve the "who spoke when" problem. Although the standard diarization systems can achieve satisfactory results in various scenarios, they…

Spiking neural networks (SNNs) offer a promising pathway to implement deep neural networks (DNNs) in a more energy-efficient manner since their neurons are sparsely activated and inferences are event-driven. However, there have been very…

The human brain utilizes spikes for information transmission and dynamically reorganizes its network structure to boost energy efficiency and cognitive capabilities throughout its lifespan. Drawing inspiration from this spike-based…

Enhancing noisy speech is an important task to restore its quality and to improve its intelligibility. In traditional non-machine-learning (ML) based approaches the parameters required for noise reduction are estimated blindly from the…

Despite the remarkable progress recently made in distant speech recognition, state-of-the-art technology still suffers from a lack of robustness, especially when adverse acoustic conditions characterized by non-stationary noises and…

Spiking neural networks (SNNs) have garnered interest due to their energy efficiency and superior effectiveness on neuromorphic chips compared with traditional artificial neural networks (ANNs). One of the mainstream approaches to…

This paper presents a dynamic network rewiring (DNR) method to generate pruned deep neural network (DNN) models that are robust against adversarial attacks yet maintain high accuracy on clean images. In particular, the disclosed DNR method…

Inference for Deep Neural Networks is increasingly being executed locally on mobile and embedded platforms due to its advantages in latency, privacy and connectivity. Since modern System on Chips typically execute a combination of different…

This paper describes speech enhancement for realtime automatic speech recognition (ASR) in real environments. A standard approach to this task is to use neural beamforming that can work efficiently in an online manner. It estimates the…

In this work, we present an analysis of a DNN-based autoencoder for speech enhancement, dereverberation and denoising. The target application is a robust speaker verification (SV) system. We start our approach by carefully designing a data…

Spiking Neural Networks (SNNs) have been attached great importance due to their biological plausibility and high energy-efficiency on neuromorphic chips. As these chips are usually resource-constrained, the compression of SNNs is thus…