Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model
Graph Chatbot
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.
Over the past few years, there have been fundamental breakthroughs in core problems in machine learning, largely driven by advances in deep neural networks. The amount of annotated data drastically increased and supervised deep discriminative models exceed ...
Artificial intelligence (AI) and machine learning (ML) have become de facto tools in many real-life applications to offer a wide range of benefits for individuals and our society. A classic ML model is typically trained with a large-scale static dataset in ...
Language independent query-by-example spoken term detection (QbE-STD) is the problem of retrieving audio documents from an archive, which contain a spoken query provided by a user. This is usually casted as a hypothesis testing and pattern matching problem ...
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 ...
EUROPEAN ASSOC SIGNAL SPEECH & IMAGE PROCESSING-EURASIP2021
In this paper, we explore various approaches for semi-
supervised learning in an end-to-end automatic speech recog-
nition (ASR) framework. The first step in our approach in-
volves training a seed model on the limited amount of labelled
data. Additional u ...
Overview Cough audio signal classification has been successfully used to diagnose a variety of respiratory conditions, and there has been significant interest in leveraging Machine Learning (ML) to provide widespread COVID-19 screening. Th ...
Learning in the brain is poorly understood and learning rules that respect biological constraints, yet yield deep hierarchical representations, are still unknown. Here, we propose a learning rule that takes inspiration from neuroscience and recent advances ...
In this work, we propose lattice-free MMI (LFMMI) for supervised adaptation of self-supervised pretrained acoustic model. We pretrain a Transformer model on thousand hours of untranscribed Librispeech data followed by supervised adaptation with LFMMI on th ...
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 ...
A major challenge in the common approach of hot water generation in residential houses lies in the highly stochastic nature of domestic hot water (DHW) demand. Learning hot water use behavior enables water heating systems to continuously adapt to the stoch ...
