Single-Handed Eyes-Free Universal Input Device

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Text-to-image models, such as Stable Diffusion, can generate high-quality images from simple textual prompts. With methods such as Textual Inversion, it is possible to expand the vocabulary of these models with additional concepts, by learning the vocabula ...

This work proposes a multi-agent filtering algorithm over graphs for finite-state hidden Markov models (HMMs), which can be used for sequential state estimation or for tracking opinion formation over dynamic social networks. We show that the difference fro ...

Universal inference enables the construction of confidence intervals and tests without regularity conditions by splitting the data into two parts and appealing to Markov's inequality. Previous investigations have shown that the cost of this generality is a ...

Adaptability and ease of programming are key features necessary for a wider spread of robotics in factories and everyday assistance. Learning from demonstration (LfD) is an approach to address this problem. It aims to develop algorithms and interfaces such ...

We propose an information theoretic framework for quantitative assessment of acoustic models used in hidden Markov model (HMM) based automatic speech recognition (ASR). The HMM backend expects that (i) the acoustic model yields accurate state conditional e ...

Musical grammar describes a set of principles that are used to understand and interpret the structure of a piece according to a musical style. The main topic of this study is grammar induction for harmony --- the process of learning structural principles f ...

State-of-the-art acoustic models for Automatic Speech Recognition (ASR) are based on Hidden Markov Models (HMM) and Deep Neural Networks (DNN) and often require thousands of hours of transcribed speech data during training. Therefore, building multilingual ...

Random codes based on quasigroups (RCBQ) are cryptcodes, i.e. they are error-correcting codes, which provide information security. Cut-Decoding and 4-Sets-Cut-Decoding algorithms for these codes are defined elsewhere. Also, the performance of these codes f ...

In the first part of this thesis, we present and compare several approaches for the determination of the steady-state of large-scale Markov chains with an underlying low-rank tensor structure. Such structure is, in our context of interest, associated with ...

Despite many behavioral and neuroimaging investigations, it remains unclear how the human cortex represents spectrotemporal sound features during auditory imagery, and how this representation compares to auditory perception. To assess this, we recorded ele ...

Humans are comparison machines: comparing and choosing an item among a set of alternatives (such as objects or concepts) is arguably one of the most natural ways for us to express our preferences and opinions. In many applications, the analysis of data con ...

Markov chains that describe interacting subsystems suffer from state space explosion but lead to highly structured matrices. In this work, we propose a novel tensor-based algorithm to address such tensor-structured Markov chains. Our algorithm combines a t ...

Conventional deep neural networks (DNN) for speech acoustic modeling rely on Gaussian mixture models (GMM) and hidden Markov model (HMM) to obtain binary class labels as the targets for DNN training. Subword classes in speech recognition systems correspond ...

The problem of acquiring multiple tasks from demonstration is typi- cally divided in two sequential processes: (1) the segmentation or identification of different subgoals/subtasks and (2) a separate learning process that parameterizes a control policy for ...

We propose to model the acoustic space of deep neural network (DNN) class-conditional posterior probabilities as a union of low- dimensional subspaces. To that end, the training posteriors are used for dictionary learning and sparse coding. Sparse represen ...

Scratchpad memory (SPM) is widely used in modern embedded processors to overcome the limitations of cache memory. The high vulnerability of SPM to soft errors, however, limits its usage in safety-critical applications. This paper proposes an efficient faul ...

State-of-the-art wearable devices such as embedded biomedical monitoring systems apply voltage scaling to lower as much as possible their energy consumption and achieve longer battery lifetimes. While embedded memories often rely on Error Correction Codes ...

Stochastic models for interacting processes feature a dimensionality that grows exponentially with the number of processes. This state space explosion severely impairs the use of standard methods for the numerical analysis of such Markov chains. In this wo ...

As different text input devices lead to different typing error patterns, considering the device characteristics when designing an error correction mechanism can lead to significantly improved results. In this paper, we propose and evaluate a spelling corre ...

Inherently error-resilient applications in areas such as signal processing, machine learning and data analytics provide opportunities for relaxing reliability requirements, and thereby reducing the overheads incurred by conventional error correction scheme ...

Single-Handed Eyes-Free Universal Input Device

Chat with Graph Search

VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text

Hidden Markov Modeling Over Graphs

A note on universal inference

Product of experts for robot learning from demonstration

On quantifying the quality of acoustic models in hybrid DNN-HMM ASR

The Learnability of the Grammar of Jazz: Bayesian Inference of Hierarchical Structures in Harmony

Multilingual Training and Adaptation in Speech Recognition

Gaussian channel transmission of images and audio files using cryptcoding

Low-rank tensor methods for large Markov chains and forward feature selection methods

Neural encoding of auditory features during music perception and imagery

Efficient Learning from Comparisons

Multigrid Methods Combined With Low-Rank Approximation For Tensor-Structured Markov Chains

Low-rank and Sparse Soft Targets to Learn Better DNN Acoustic Models

Learning Stable Task Sequences from Demonstration with Linear Parameter Varying Systems and Hidden Markov Models

Exploiting Low-dimensional Structures to Enhance DNN based Acoustic Modeling in Speech Recognition

A Cache-Assisted Scratchpad Memory for Multiple-Bit-Error Correction

Energy vs. Reliability Trade-offs Exploration in Biomedical Ultra-Low Power Devices

Finding Steady States of Communicating Markov Processes Combining Aggregation/Disaggregation with Tensor Techniques

HMM-Based Error Correction Mechanism for Five-Key Chording Keyboards

Mitigating the Impact of Faults in Unreliable Memories For Error-Resilient Applications