相关论文: Interpretable Deep Learning Model for the Detectio…

We investigate the effectiveness of convolutive prediction, a novel formulation of linear prediction for speech dereverberation, for speaker separation in reverberant conditions. The key idea is to first use a deep neural network (DNN) to…

Accurately detecting dysfluencies in spoken language can help to improve the performance of automatic speech and language processing components and support the development of more inclusive speech and language technologies. Inspired by the…

Inference and prediction under partial knowledge of a physical system is challenging, particularly when multiple confounding sources influence the measured response. Explicitly accounting for these influences in physics-based models is…

The autoencoder is an unsupervised learning paradigm that aims to create a compact latent representation of data by minimizing the reconstruction loss. However, it tends to overlook the fact that most data (images) are embedded in a…

We propose an algorithm to denoise speakers from a single microphone in the presence of non-stationary and dynamic noise. Our approach is inspired by the recent success of neural network models separating speakers from other speakers and…

The joint optimization of the reconstruction and classification error is a hard non convex problem, especially when a non linear mapping is utilized. In order to overcome this obstacle, a novel optimization strategy is proposed, in which a…

A fundamental challenge in neuroscience is to understand what structure in the world is represented in spatially distributed patterns of neural activity from multiple single-trial measurements. This is often accomplished by learning a…

The aim of latent variable disentanglement is to infer the multiple informative latent representations that lie behind a data generation process and is a key factor in controllable data generation. In this paper, we propose a deep neural…

Pre-trained Transformer language models (LM) have become go-to text representation encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences and passages into single dense vector representations for efficient…

Over the recent years, various deep learning-based embedding methods have been proposed and have shown impressive performance in speaker verification. However, as in most of the classical embedding techniques, the deep learning-based…

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned…

The amount of articulatory data available for training deep learning models is much less compared to acoustic speech data. In order to improve articulatory-to-acoustic synthesis performance in these low-resource settings, we propose a…

Learning useful representations of complex data has been the subject of extensive research for many years. With the diffusion of Deep Neural Networks, Variational Autoencoders have gained lots of attention since they provide an explicit…

Speech restoration aims at restoring full-band speech with high quality and intelligibility, considering a diverse set of distortions. MaskSR is a recently proposed generative model for this task. As other models of its kind, MaskSR attains…

Automatic speech recognition in reverberant conditions is a challenging task as the long-term envelopes of the reverberant speech are temporally smeared. In this paper, we propose a neural model for enhancement of sub-band temporal…

Intent is defined for understanding spoken language in existing works. Both textual features and acoustic features involved in medical speech contain intent, which is important for symptomatic diagnosis. In this paper, we propose a medical…

Dysarthric speech exhibits abnormal prosody and significant speaker variability, presenting persistent challenges for automatic speech recognition (ASR). While text-to-speech (TTS)-based data augmentation has shown potential, existing…

The electroencephalogram (EEG) is a powerful method to understand how the brain processes speech. Linear models have recently been replaced for this purpose with deep neural networks and yield promising results. In related EEG…

Deep learning has the potential to enhance speech signals and increase their intelligibility for users of hearing aids. Deep models suited for real-world application should feature a low computational complexity and low processing delay of…

Speech contains information that is clinically relevant to some diseases, which has the potential to be used for health assessment. Recent work shows an interest in applying deep learning algorithms, especially pretrained large speech…