On matching data and model in LF-MMI-based dysarthric speech recognition

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.

Earth scientists study a variety of problems with remote sensing data, but they most often consider them in isolation from each other, which limits information flows across disciplines. In this work, we present METEOR, a meta-learning methodology for Earth ...

Atypical aspects in speech concern speech that deviates from what is commonly considered normal or healthy. In this thesis, we propose novel methods for detection and analysis of these aspects, e.g. to monitor the temporary state of a speaker, diseases tha ...

Speech recognition-based applications upon the advancements in artificial intelligence play an essential role to transform most aspects of modern life. However, speech recognition in real-life conditions (e.g., in the presence of overlapping speech, varyin ...

Models trained with counterfactually augmented data learn representations of the causal structure of tasks, enabling robust generalization. However, high-quality counterfactual data is scarce for most tasks and not easily generated at scale. When crowdsour ...

The recent rise in both popularity and performance of large language models has garnered considerable interest regarding their applicability to education. Technologies like ChatGPT, which can engage in human-like dialog, have already disrupted educational ...

The recent advance of large language models (LLMs) demonstrates that these large-scale foundation models achieve remarkable capabilities across a wide range of language tasks and domains. The success of the statistical learning approach challenges our unde ...

As text generative models can give increasingly long answers, we tackle the problem of synthesizing long text in digital ink. We show that the commonly used models for this task fail to generalize to long-form data and how this problem can be solved by aug ...

Biological motor control is versatile, efficient, and depends on proprioceptive feedback. Muscles are flexible and undergo continuous changes, requiring distributed adaptive control mechanisms that continuously account for the body's state. The canonical r ...

In this paper we propose a novel virtual simulation-pilot engine for speeding up air traffic controller (ATCo) training by integrating different state-of-the-art artificial intelligence (AI)-based tools. The virtual simulation-pilot engine receives spoken ...

Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks. However, it is largely unexplored whether they can better internalize knowledge from a structured data, such as a knowledge graph, or from ...

Training deep neural network based Automatic Speech Recognition (ASR) models often requires thousands of hours of transcribed data, limiting their use to only a few languages. Moreover, current state-of-the-art acoustic models are based on the Transformer ...

Current task-oriented dialog (TOD) systems mostly manage structured knowledge (e.g. databases and tables) to guide the goal-oriented conversations. However, they fall short of handling dialogs which also involve unstructured knowledge (e.g. reviews and doc ...

Term extraction is an information extraction task at the root of knowledge discovery platforms. Developing term extractors that are able to generalize across very diverse and potentially highly technical domains is challenging, as annotations for domains r ...

Remote sensing visual question answering (RSVQA) opens new avenues to promote the use of satellites data, by interfacing satellite image analysis with natural language processing. Capitalizing on the remarkable advances in natural language processing and c ...

Recent developments in speech emotion recognition (SER) often leverage deep neural networks (DNNs). Comparing and benchmarking different DNN models can often be tedious due to the use of different datasets and evaluation protocols. To facilitate the proces ...

Natural Language Processing (NLP) has become increasingly utilized to provide adaptivity in educational applications. However, recent research has highlighted a variety of biases in pre-trained language models. While existing studies investigate bias in di ...

In many situations, the data one has access to at test time follows a different distribution from the training data. Over the years, this problem has been tackled by closed-set domain adaptation techniques. Recently, open-set domain adaptation has emerged ...

Recent breakthroughs in deep learning often rely on representation learning and knowledge transfer. In recent years, unsupervised and self-supervised techniques for learning speech representation were developed to foster automatic speech recognition. Up to ...

Speech signal conveys several kinds of information such as a message, speaker identity, emotional state of the speaker and social state of the speaker. Automatic speech assessment is a broad area that refers to using automatic methods to predict human judg ...

Transformer-based language models trained on large text corpora have enjoyed immense popularity in the natural language processing community and are commonly used as a starting point for downstream tasks. While these models are undeniably useful, it is a c ...

On matching data and model in LF-MMI-based dysarthric speech recognition

Chat with Graph Search

Meta-learning to address diverse Earth observation problems across resolutions

Novel Methods For Detection And Analysis Of Atypical Aspects In Speech

Sparse Autoencoders for Speech Modeling and Recognition

DISCO: Distilling Counterfactuals with Large Language Models

Prompting Large Language Models to Power Educational Chatbots

Monotonicity Reasoning in the Age of Neural Foundation Models

DSS: Synthesizing Long Digital Ink Using Data Augmentation, Style Encoding and Split Generation

Contrasting action and posture coding with hierarchical deep neural network models of proprioception

A Virtual Simulation-Pilot Agent for Training of Air Traffic Controllers

SKILL: Structured Knowledge Infusion for Large Language Models

Efficient Transformer-Based Speech Recognition

End-to-End Task-Oriented Dialog Modeling With Semi-Structured Knowledge Management

Unsupervised Term Extraction for Highly Technical Domains

Language Transformers for Remote Sensing Visual Question Answering

Serab: A Multi-Lingual Benchmark For Speech Emotion Recognition

Bias at a Second Glance: A Deep Dive into Bias for German Educational Peer-Review Data Modeling

Learning to Generate the Unknowns as a Remedy to the Open-Set Domain Shift

Word-level Embeddings for Cross-Task Transfer Learning in Speech Processing

Novel Methods for Incorporating Prior Knowledge for Automatic Speech Assessment

Interpreting Language Models Through Knowledge Graph Extraction