Related papers: Shaking Acoustic Spectral Sub-bands Can Better Reg…

Time series classification(TSC) has always been an important and challenging research task. With the wide application of deep learning, more and more researchers use deep learning models to solve TSC problems. Since time series always…

This work presents a new method for enhancing communication efficiency in stochastic Federated Learning that trains over-parameterized random networks. In this setting, a binary mask is optimized instead of the model weights, which are kept…

Speech emotion recognition (SER) has made significant strides with the advent of powerful self-supervised learning (SSL) models. However, the generalization of these models to diverse languages and emotional expressions remains a challenge.…

This paper proposes a full-band and sub-band fusion model, named as FullSubNet, for single-channel real-time speech enhancement. Full-band and sub-band refer to the models that input full-band and sub-band noisy spectral feature, output…

We consider the problem of streaming kernel regression, when the observations arrive sequentially and the goal is to recover the underlying mean function, assumed to belong to an RKHS. The variance of the noise is not assumed to be known.…

Affective Behavior Analysis is an important part in human-computer interaction. Existing multi-task affective behavior recognition methods suffer from the problem of incomplete labeled datasets. To tackle this problem, this paper presents a…

We propose a new iterative unfolding method for experimental data, making use of a regularization function. The use of this function allows one to build an improved normalization procedure for Monte Carlo spectra, unbiased by the presence…

Fueled by recent advances of self-supervised models, pre-trained speech representations proved effective for the downstream speech emotion recognition (SER) task. Most prior works mainly focus on exploiting pre-trained representations and…

Normalization techniques play an important role in supporting efficient and often more effective training of deep neural networks. While conventional methods explicitly normalize the activations, we suggest to add a loss term instead. This…

Deep neural network based full-band speech enhancement systems face challenges of high demand of computational resources and imbalanced frequency distribution. In this paper, a light-weight full-band model is proposed with two dedicated…

Aspect level sentiment classification is a fine-grained sentiment analysis task. To detect the sentiment towards a particular aspect in a sentence, previous studies have developed various attention-based methods for generating…

A fundamental challenge in developing semantic parsers is the paucity of strong supervision in the form of language utterances annotated with logical form. In this paper, we propose to exploit structural regularities in language in…

The task of few-shot GAN adaptation aims to adapt a pre-trained GAN model to a small dataset with very few training images. While existing methods perform well when the dataset for pre-training is structurally similar to the target dataset,…

Non-speech emotion recognition has a wide range of applications including healthcare, crime control and rescue, and entertainment, to name a few. Providing these applications using edge computing has great potential, however, recent studies…

We propose a novel method to model hierarchical metrical structures for both symbolic music and audio signals in a self-supervised manner with minimal domain knowledge. The model trains and inferences on beat-aligned music signals and…

Data-driven machine learning models are being increasingly employed in several important inference problems in biology, chemistry, and physics which require learning over combinatorial spaces. Recent empirical evidence (see, e.g., [1], [2],…

Deep convolutional neural networks are known to be unstable during training at high learning rate unless normalization techniques are employed. Normalizing weights or activations allows the use of higher learning rates, resulting in faster…

Speech recognition system performance degrades in noisy environments. If the acoustic models are built using features of clean utterances, the features of a noisy test utterance would be acoustically mismatched with the trained model. This…

We present an electrocardiogram (ECG) -based emotion recognition system using self-supervised learning. Our proposed architecture consists of two main networks, a signal transformation recognition network and an emotion recognition network.…

Although automatic emotion recognition (AER) has recently drawn significant research interest, most current AER studies use manually segmented utterances, which are usually unavailable for dialogue systems. This paper proposes integrating…