Related papers: A Framework for Generative and Contrastive Learnin…

Contrastive learning is an approach to representation learning that utilizes naturally occurring similar and dissimilar pairs of data points to find useful embeddings of data. In the context of document classification under topic modeling…

We present a self-supervised learning method to learn audio and video representations. Prior work uses the natural correspondence between audio and video to define a standard cross-modal instance discrimination task, where a model is…

Accurate classification of articulatory-phonological features plays a vital role in understanding human speech production and developing robust speech technologies, particularly in clinical contexts where targeted phonemic analysis and…

Contrastive learning-based recommendation algorithms have significantly advanced the field of self-supervised recommendation, particularly with BPR as a representative ranking prediction task that dominates implicit collaborative filtering.…

Modeling various aspects that make a music piece unique is a challenging task, requiring the combination of multiple sources of information. Deep learning is commonly used to obtain representations using various sources of information, such…

Recent multimodal models such as Contrastive Language-Image Pre-training (CLIP) have shown remarkable ability to align visual and linguistic representations. However, domains where small visual differences carry large semantic significance,…

Text-to-image (T2I) generation aims at producing realistic images corresponding to text descriptions. Generative Adversarial Network (GAN) has proven to be successful in this task. Typical T2I GANs are 2 phase methods that first pretrain an…

Contrastive learning has become a popular approach in natural language processing, particularly for the learning of sentence embeddings. However, the discrete nature of natural language makes it difficult to ensure the quality of positive…

In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disentanglement, we propose…

Cued Speech (CS) is a communication system for deaf people or hearing impaired people, in which a speaker uses it to aid a lipreader in phonetic level by clarifying potentially ambiguous mouth movements with hand shape and positions.…

Contrastive learning has delivered impressive results for various tasks in the self-supervised regime. However, existing approaches optimize for learning representations specific to downstream scenarios, i.e., \textit{global}…

The goal of this work is to train robust speaker recognition models without speaker labels. Recent works on unsupervised speaker representations are based on contrastive learning in which they encourage within-utterance embeddings to be…

Contrastive self-supervised learning methods famously produce high quality transferable representations by learning invariances to different data augmentations. Invariances established during pre-training can be interpreted as strong…

Vocoder models have recently achieved substantial progress in generating authentic audio comparable to human quality while significantly reducing memory requirement and inference time. However, these data-hungry generative models require…

In recent Text-to-Speech (TTS) systems, a neural vocoder often generates speech samples by solely conditioning on acoustic features predicted from an acoustic model. However, there are always distortions existing in the predicted acoustic…

As an algorithmic framework for learning to learn, meta-learning provides a promising solution for few-shot text classification. However, most existing research fail to give enough attention to class labels. Traditional basic framework…

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance…

This paper addresses the persistent challenge in Keyword Spotting (KWS), a fundamental component in speech technology, regarding the acquisition of substantial labeled data for training. Given the difficulty in obtaining large quantities of…

Overlapping sound events are ubiquitous in real-world environments, but existing end-to-end sound event detection (SED) methods still struggle to detect them effectively. A critical reason is that these methods represent overlapping events…

Learning a discriminative semantic space using unlabelled and noisy data remains unaddressed in a multi-label setting. We present a contrastive self-supervised learning method which is robust to data noise, grounded in the domain of…