Related papers: Efficient Implementation of the Room Simulator for…

This paper introduces a practical approach for leveraging a real-time deep learning model to alternate between speech enhancement and joint speech enhancement and separation depending on whether the input mixture contains one or two active…

We show in this work that memory intensive computations can result in severe performance problems due to off-chip memory access and CPU-GPU context switch overheads in a wide range of deep learning models. For this problem, current…

While deep neural networks have shown powerful performance in many audio applications, their large computation and memory demand has been a challenge for real-time processing. In this paper, we study the impact of scaling the precision of…

Challenging the Nvidia monopoly, dedicated AI-accelerator chips have begun emerging for tackling the computational challenge that the inference and, especially, the training of modern deep neural networks (DNNs) poses to modern computers.…

Acoustic models in real-time speech recognition systems typically stack multiple unidirectional LSTM layers to process the acoustic frames over time. Performance improvements over vanilla LSTM architectures have been reported by prepending…

Analog Compute-In-Memory (CIM) architectures promise significant energy efficiency gains for neural network inference, but suffer from complex hardware-induced noise that poses major challenges for deployment. While noise-aware training…

Room impulse response (RIR) generation remains a critical challenge for creating immersive virtual acoustic environments. Current methods suffer from two fundamental limitations: the scarcity of full-band RIR datasets and the inability of…

Background: Active noise cancellation has been a subject of research for decades. Traditional techniques, like the Fast Fourier Transform, have limitations in certain scenarios. This research explores the use of deep neural networks (DNNs)…

Autonomous learning of dexterous, long-horizon robotic skills has been a longstanding pursuit of embodied AI. Recent advances in robotic reinforcement learning (RL) have demonstrated remarkable performance and robustness in real-world…

Training deep neural networks at the edge on light computational devices, embedded systems and robotic platforms is nowadays very challenging. Continual learning techniques, where complex models are incrementally trained on small batches of…

Spoken language understanding (SLU) system usually consists of various pipeline components, where each component heavily relies on the results of its upstream ones. For example, Intent detection (ID), and slot filling (SF) require its…

Finding ways to accelerate text input for individuals with profound motor impairments has been a long-standing area of research. Closing the speed gap for augmentative and alternative communication (AAC) devices such as eye-tracking…

Fast Fourier Transforms (FFT) are widely used to reduce memory and computational costs in deep learning. However, existing implementations, including standard FFT and real FFT (rFFT), cannot achieve true in-place computation. In particular,…

Sampled environment transitions are a critical input to deep reinforcement learning (DRL) algorithms. Current DRL benchmarks often allow for the cheap and easy generation of large amounts of samples such that perceived progress in DRL does…

We are interested in solving the problem of imitation learning with a limited amount of real-world expert data. Existing offline imitation methods often struggle with poor data coverage and severe performance degradation. We propose a…

Conventional far-field automatic speech recognition (ASR) systems typically employ microphone array techniques for speech enhancement in order to improve robustness against noise or reverberation. However, such speech enhancement techniques…

Automatic speech recognition (ASR) is a relevant area in multiple settings because it provides a natural communication mechanism between applications and users. ASRs often fail in environments that use language specific to particular…

In recent years, large language models have achieved great success due to their unprecedented size. However, training these models poses a challenge for most researchers as it requires a substantial number of GPUs. To reduce GPU memory…

In recent years, significant progress has been made in the field of robotic reinforcement learning (RL), enabling methods that handle complex image observations, train in the real world, and incorporate auxiliary data, such as…

We propose a neural network model that can separate target speech sources from interfering sources at different angular regions using two microphones. The model is trained with simulated room impulse responses (RIRs) using omni-directional…