Related papers: Learning Filterbanks from Raw Speech for Phone Rec…

Neural network-based vocoders have recently demonstrated the powerful ability to synthesize high-quality speech. These models usually generate samples by conditioning on spectral features, such as Mel-spectrogram and fundamental frequency,…

We investigate sequence machine learning techniques on raw radio signal time-series data. By applying deep recurrent neural networks we learn to discriminate between several application layer traffic types on top of a constant envelope…

Deep learning models are intrinsically sensitive to distribution shifts in the input data. In particular, small, barely perceivable perturbations to the input data can force models to make wrong predictions with high confidence. An common…

Acoustic beamformers have been widely used to enhance audio signals. Currently, the best methods are the deep neural network (DNN)-powered variants of the generalized eigenvalue and minimum-variance distortionless response beamformers and…

Convolutional neural networks (CNNs) with dilated filters such as the Wavenet or the Temporal Convolutional Network (TCN) have shown good results in a variety of sequence modelling tasks. However, efficiently modelling long-term…

In the last decade convolutional neural networks have become gargantuan. Pre-trained models, when used as initializers are able to fine-tune ever larger networks on small datasets. Consequently, not all the convolutional features that these…

Wireless communications at high-frequency bands with large antenna arrays face challenges in beam management, which can potentially be improved by multimodality sensing information from cameras, LiDAR, radar, and GPS. In this paper, we…

Recently there has been a lot of work on pruning filters from deep convolutional neural networks (CNNs) with the intention of reducing computations.The key idea is to rank the filters based on a certain criterion (say, l1-norm) and retain…

Deepfake (DF) attacks pose a growing threat as generative models become increasingly advanced. However, our study reveals that existing DF datasets fail to deceive human perception, unlike real DF attacks that influence public discourse. It…

Convolutional layers with 1-D filters are often used as frontend to encode audio signals. Unlike fixed time-frequency representations, they can adapt to the local characteristics of input data. However, 1-D filters on raw audio are hard to…

A novel procedure is presented in this paper, for training a deep convolutional and recurrent neural network, taking into account both the available training data set and some information extracted from similar networks trained with other…

In recent years, using raw waveforms as input for deep networks has been widely explored for the speaker verification system. For example, RawNet and RawNet2 extracted speaker's feature embeddings from waveforms automatically for…

A well-trained Convolutional Neural Network can easily be pruned without significant loss of performance. This is because of unnecessary overlap in the features captured by the network's filters. Innovations in network architecture such as…

Fully exploiting ad-hoc microphone networks for distant speech recognition is still an open issue. Empirical evidence shows that being able to select the best microphone leads to significant improvements in recognition without any…

We investigated how the application of deep learning, specifically the use of convolutional networks trained with GPUs, can help to build better predictive models in telecommunication business environments, and fill this gap. In particular,…

Sequence-to-sequence models have shown success in end-to-end speech recognition. However these models have only used shallow acoustic encoder networks. In our work, we successively train very deep convolutional networks to add more…

Deep learning approaches for beat and downbeat tracking have brought advancements. However, these approaches continue to rely on hand-crafted, subsampled spectral features as input, restricting the information available to the model. In…

We introduce a new audio processing technique that increases the sampling rate of signals such as speech or music using deep convolutional neural networks. Our model is trained on pairs of low and high-quality audio examples; at test-time,…

The goal of continuous emotion recognition is to assign an emotion value to every frame in a sequence of acoustic features. We show that incorporating long-term temporal dependencies is critical for continuous emotion recognition tasks. To…

We present an architecture of a recurrent neural network (RNN) with a fully-connected deep neural network (DNN) as its feature extractor. The RNN is equipped with both causal temporal prediction and non-causal look-ahead, via…