Related papers: Empirical Evaluation of Deep Learning Model Compre…

How can we compress language models without sacrificing accuracy? The number of compression algorithms for language models is rapidly growing to benefit from remarkable advances of recent language models without side effects due to the…

Deep neural networks (DNNs) continue to make significant advances, solving tasks from image classification to translation or reinforcement learning. One aspect of the field receiving considerable attention is efficiently executing deep…

We consider the optimization of deep convolutional neural networks (CNNs) such that they provide good performance while having reduced complexity if deployed on either conventional systems utilizing spatial-domain convolution or lower…

FullSubNet is our recently proposed real-time single-channel speech enhancement network that achieves outstanding performance on the Deep Noise Suppression (DNS) Challenge dataset. A number of variants of FullSubNet have been proposed, but…

Current audio deepfake detection has achieved remarkable performance using diverse deep learning architectures such as ResNet, and has seen further improvements with the introduction of large models (LMs) like Wav2Vec. The success of large…

Efficient deployment of large audio-language models for speech translation remains challenging due to their significant computational requirements. In this paper, we address this challenge through our system submissions to the "Model…

Modern compression algorithms are often the result of laborious domain-specific research; industry standards such as MP3, JPEG, and AMR-WB took years to develop and were largely hand-designed. We present a deep neural network model which…

Agglomerative models have recently emerged as a powerful approach to training vision foundation models, leveraging multi-teacher distillation from existing models such as CLIP, DINO, and SAM. This strategy enables the efficient creation of…

Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…

We introduce VampNet, a masked acoustic token modeling approach to music synthesis, compression, inpainting, and variation. We use a variable masking schedule during training which allows us to sample coherent music from the model by…

Deep neural speech and audio processing systems have a large number of trainable parameters, a relatively complex architecture, and require a vast amount of training data and computational power. These constraints make it more challenging…

Masked Language Modeling (MLM) is widely used to pretrain language models. The standard random masking strategy in MLM causes the pre-trained language models (PLMs) to be biased toward high-frequency tokens. Representation learning of rare…

Existing speech processing systems consist of different modules, individually optimized for a specific task such as acoustic modelling or feature extraction. In addition to not assuring optimality of the system, the disjoint nature of…

This paper proposes a novel approach that uses deep neural networks for classifying imagined speech, significantly increasing the classification accuracy. The proposed approach employs only the EEG channels over specific areas of the brain…

Speech recognition in noisy and channel distorted scenarios is often challenging as the current acoustic modeling schemes are not adaptive to the changes in the signal distribution in the presence of noise. In this work, we develop a novel…

Recent advances in deep learning have markedly improved the quality of visual-attention modelling. In this work we apply these advances to video compression. We propose a compression method that uses a saliency model to adaptively compress…

AI's widespread integration has led to neural networks (NNs) deployment on edge and similar limited-resource platforms for safety-critical scenarios. Yet, NN's fragility raises concerns about reliable inference. Moreover, constrained…

Deep neural networks have achieved strong performance in image classification tasks due to their ability to learn complex patterns from high-dimensional data. However, their large computational and memory requirements often limit deployment…

Neural network-based Text-to-Speech has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron2, FastSpeech, FastPitch) usually generate Mel-spectrogram from text and then synthesize speech using vocoder…

Sparse tensors appear frequently in distributed deep learning, either as a direct artifact of the deep neural network's gradients, or as a result of an explicit sparsification process. Existing communication primitives are agnostic to the…