Related papers: Device-aware inference operations in SONOS nonvola…

An accurate objective speech intelligibility prediction algorithms is of great interest for many applications such as speech enhancement for hearing aids. Most algorithms measures the signal-to-noise ratios or correlations between the…

Robust loss minimization is an important strategy for handling robust learning issue on noisy labels. Current approaches for designing robust losses involve the introduction of noise-robust factors, i.e., hyperparameters, to control the…

Keyword spotting accuracy degrades when neural networks are exposed to noisy environments. On-site adaptation to previously unseen noise is crucial to recovering accuracy loss, and on-device learning is required to ensure that the…

Speech enhancement in ad-hoc microphone arrays is often hindered by the asynchronization of the devices composing the microphone array. Asynchronization comes from sampling time offset and sampling rate offset which inevitably occur when…

Multilayered artificial neural networks (ANN) have found widespread utility in classification and recognition applications. The scale and complexity of such networks together with the inadequacies of general purpose computing platforms have…

Nowadays, one practical limitation of deep neural network (DNN) is its high degree of specialization to a single task or domain (e.g., one visual domain). It motivates researchers to develop algorithms that can adapt DNN model to multiple…

Deep-learning based noise reduction algorithms have proven their success especially for non-stationary noises, which makes it desirable to also use them for embedded devices like hearing aids (HAs). This, however, is currently not possible…

In the autoencoder based anomaly detection paradigm, implementing the autoencoder in edge devices capable of learning in real-time is exceedingly challenging due to limited hardware, energy, and computational resources. We show that these…

Energy-efficient deep neural network (DNN) accelerators are prone to non-idealities that degrade DNN performance at inference time. To mitigate such degradation, existing methods typically add perturbations to the DNN weights during…

Label noise is a critical factor that degrades the generalization performance of deep neural networks, thus leading to severe issues in real-world problems. Existing studies have employed strategies based on either loss or uncertainty to…

Despite the significant improvements in speaker recognition enabled by deep neural networks, unsatisfactory performance persists under noisy environments. In this paper, we train the speaker embedding network to learn the "clean" embedding…

This paper addresses the challenging problem of energy-efficient and uncertainty-aware pose estimation in insect-scale drones, which is crucial for tasks such as surveillance in constricted spaces and for enabling non-intrusive spatial…

Many industrial applications use Metric Learning as a way to circumvent scalability issues when designing systems with a high number of classes. Because of this, this field of research is attracting a lot of interest from the academic and…

The quality of quantum bits (qubits) in silicon is highly vulnerable to charge noise that is omni-present in semiconductor devices and is in principle hard to be suppressed. For a realistically sized quantum dot system based on a…

Invariance to microphone array configuration is a rare attribute in neural beamformers. Filter-and-sum (FS) methods in this class define the target signal with respect to a reference channel. However, this not only complicates formulation…

Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. While optimizations have been proposed for inference latency, memory footprint, and energy consumption, prior hardware-aware…

Active noise control (ANC) has become popular for reducing noise and thus enhancing user comfort in headphones. While feedback control offers an effective way to implement ANC, it is restricted by uncertainty of the controlled system that…

Image-based diagnostic decision support systems (DDSS) utilizing deep learning have the potential to optimize clinical workflows. However, developing DDSS requires extensive datasets with expert annotations and is therefore costly.…

Deep Neural Networks are allowing mobile devices to incorporate a wide range of features into user applications. However, the computational complexity of these models makes it difficult to run them effectively on resource-constrained mobile…

Typically, a salient object detection (SOD) model faces opposite requirements in processing object interiors and boundaries. The features of interiors should be invariant to strong appearance change so as to pop-out the salient object as a…