Related papers: BayesSpeech: A Bayesian Transformer Network for Au…

Active learning methods for neural networks are usually based on greedy criteria which ultimately give a single new design point for the evaluation. Such an approach requires either some heuristics to sample a batch of design points at one…

Recent research advances in deep neural network (DNN)-based beamformers have shown great promise for speech enhancement under adverse acoustic conditions. Different network architectures and input features have been explored in estimating…

This paper describes speech enhancement for realtime automatic speech recognition (ASR) in real environments. A standard approach to this task is to use neural beamforming that can work efficiently in an online manner. It estimates the…

In recent years, Large Language Models (LLMs) have garnered significant attention from the research community due to their exceptional performance and generalization capabilities. In this paper, we introduce a novel method for…

We introduce implicit Bayesian neural networks, a simple and scalable approach for uncertainty representation in deep learning. Standard Bayesian approach to deep learning requires the impractical inference of the posterior distribution…

interpretable, and well understood models that are routinely employed even though, as is revealed through prior and posterior predictive checks, these can poorly characterise the spatial heterogeneity in the underlying process of interest.…

Bayesian Neural Networks (BNNs) provide a probabilistic interpretation for deep learning models by imposing a prior distribution over model parameters and inferring a posterior distribution based on observed data. The model sampled from the…

In this project, we worked on speech recognition, specifically predicting individual words based on both the video frames and audio. Empowered by convolutional neural networks, the recent speech recognition and lip reading models are…

We implement a Bayesian inference process for Neural Networks to model the time to failure of highly reliable weapon systems with interval-censored data and time-varying covariates. We analyze and benchmark our approach, LaplaceNN, on…

Currently, it is hard to reap the benefits of deep learning for Bayesian methods, which allow the explicit specification of prior knowledge and accurately capture model uncertainty. We present Prior-Data Fitted Networks (PFNs). PFNs…

Text classification is a fundamental task in natural language processing (NLP). Several recent studies show the success of deep learning on text processing. Convolutional neural network (CNN), as a popular deep learning model, has shown…

Confidence estimation, in which we estimate the reliability of each recognized token (e.g., word, sub-word, and character) in automatic speech recognition (ASR) hypotheses and detect incorrectly recognized tokens, is an important function…

End-to-end speech translation models have become a new trend in research due to their potential of reducing error propagation. However, these models still suffer from the challenge of data scarcity. How to effectively use unlabeled or other…

Acoustic word embeddings --- fixed-dimensional vector representations of variable-length spoken word segments --- have begun to be considered for tasks such as speech recognition and query-by-example search. Such embeddings can be learned…

Automatic speech recognition (ASR) has become increasingly ubiquitous on modern edge devices. Past work developed streaming End-to-End (E2E) all-neural speech recognizers that can run compactly on edge devices. However, E2E ASR models are…

In industrial machine learning pipelines, data often arrive in parts. Particularly in the case of deep neural networks, it may be too expensive to train the model from scratch each time, so one would rather use a previously learned model…

In this paper, we introduce the Variational Autoencoder (VAE) to an end-to-end speech synthesis model, to learn the latent representation of speaking styles in an unsupervised manner. The style representation learned through VAE shows good…

Sequence-to-sequence (S2S) modeling is becoming a popular paradigm for automatic speech recognition (ASR) because of its ability to jointly optimize all the conventional ASR components in an end-to-end (E2E) fashion. This report…

Artificial Neural Network (ANN)-based inference on battery-powered devices can be made more energy-efficient by restricting the synaptic weights to be binary, hence eliminating the need to perform multiplications. An alternative, emerging,…

Memory-based meta-learning is a technique for approximating Bayes-optimal predictors. Under fairly general conditions, minimizing sequential prediction error, measured by the log loss, leads to implicit meta-learning. The goal of this work…