Related papers: Autoregressive Co-Training for Learning Discrete S…
We present a framework for learning disentangled and interpretable jointly continuous and discrete representations in an unsupervised manner. By augmenting the continuous latent distribution of variational autoencoders with a relaxed…
Existing studies on self-supervised speech representation learning have focused on developing new training methods and applying pre-trained models for different applications. However, the quality of these models is often measured by the…
Discrete representations of speech, obtained from Self-Supervised Learning (SSL) foundation models, are widely used, especially where there are limited data for the downstream task, such as for a low-resource language. Typically,…
Joint image-feature generative modeling has recently emerged as an effective strategy for improving diffusion training by coupling low-level VAE latents with high-level semantic features extracted from pre-trained visual encoders. However,…
Latent representation learning has been an active field of study for decades in numerous applications. Inspired among others by the tokenization from Natural Language Processing and motivated by the research of a simple data representation,…
Although many pretrained models exist for text or images, there have been relatively fewer attempts to train representations specifically for dialog understanding. Prior works usually relied on finetuned representations based on generic…
Recently, there has been a surge in the use of generated data to enhance the performance of downstream models, largely due to the advancements in pre-trained language models. However, most prevailing methods trained generative and…
Past work on story generation has demonstrated the usefulness of conditioning on a generation plan to generate coherent stories. However, these approaches have used heuristics or off-the-shelf models to first tag training stories with the…
Developing a dialogue agent that is capable of making autonomous decisions and communicating by natural language is one of the long-term goals of machine learning research. Traditional approaches either rely on hand-crafting a small…
For self-supervised speech processing, it is crucial to use pretrained models as speech representation extractors. In recent works, increasing the size of the model has been utilized in acoustic model training in order to achieve better…
Federated learning is a method of training models on private data distributed over multiple devices. To keep device data private, the global model is trained by only communicating parameters and updates which poses scalability challenges…
Large language models are shown to memorize privacy information such as social security numbers in training data. Given the sheer scale of the training corpus, it is challenging to screen and filter these privacy data, either manually or…
Learning meaningful and general representations from unannotated speech that are applicable to a wide range of tasks remains challenging. In this paper we propose to use autoregressive predictive coding (APC), a recently proposed…
Most spoken language understanding systems use a pipeline approach composed of an automatic speech recognition interface and a natural language understanding module. This approach forces hard decisions when converting continuous inputs into…
Joint machine learning models that allow synthesizing and classifying data often offer uneven performance between those tasks or are unstable to train. In this work, we depart from a set of empirical observations that indicate the…
Generative concept representations have three major advantages over discriminative ones: they can represent uncertainty, they support integration of learning and reasoning, and they are good for unsupervised and semi-supervised learning. We…
In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels. A common task is to classify augmentations or different modalities of the data, which share semantic content (e.g. an object in…
The distributed and continuous representations used by neural networks are at odds with representations employed in linguistics, which are typically symbolic. Vector quantization has been proposed as a way to induce discrete neural…
Supervisory signals have the potential to make low-dimensional data representations, like those learned by mixture and topic models, more interpretable and useful. We propose a framework for training latent variable models that explicitly…
We propose a probabilistic framework for developing computational models of biological neural systems. In this framework, physiological recordings are viewed as discrete-time partial observations of an underlying continuous-time stochastic…