Using KL-based Acoustic Models in a Large Vocabulary Recognition Task
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.
During the last 40 years, a large number of studies have analyzed car holding and use behavior. Most of these ignore the dynamics of household and driver needs that very likely drive such decisions. Our work builds up on a disaggregate (compensatory) appro ...
In the context of hybrid HMM/MLP Automatic Speech Recognition (ASR), this paper describes an investigation into a new type of stochastic phone space transformation, which maps "source" phone (or phone HMM state) posterior probabilities (as obtained at the ...
Model specification is an integral part of any statistical inference problem. Several model selection techniques have been developed in order to determine which model is the best one among a list of possible candidates. Another way to deal with this questi ...
This paper investigates detection of English keywords in a conversational scenario using a combination of acoustic and LVCSR based keyword spotting systems. Acoustic KWS systems search predefined words in parameterized spoken data. Corresponding confidence ...
In this paper, we propose a novel framework to integrate articulatory features (AFs) into HMM- based ASR system. This is achieved by using posterior probabilities of different AFs (estimated by multilayer perceptrons) directly as observation features in Ku ...
We hypothesize that optimal deep neural networks (DNN) class-conditional posterior probabilities live in a union of low-dimensional subspaces. In real test conditions, DNN posteriors encode uncertainties which can be regarded as a superposition of unstruct ...
We study the distributed inference task over regression and classification models where the likelihood function is strongly log-concave. We show that diffusion strategies allow the KL divergence between two likelihood functions to converge to zero at the r ...
Automatic speech recognition (ASR) is a fascinating area of research towards realizing humanmachine interactions. After more than 30 years of exploitation of Gaussian Mixture Models (GMMs), state-of-the-art systems currently rely on Deep Neural Network (DN ...
Many speech technology systems rely on Gaussian Mixture Models (GMMs). The need for a comparison between two GMMs arises in applications such as speaker verification, model selection or parameter estimation. For this purpose, the Kullback-Leibler (KL) dive ...
This paper investigates detection of English keywords in a conversational scenario using a combination of acoustic and LVCSR based keyword spotting systems. Acoustic KWS systems search predefined words in parameterized spoken data. Corresponding confidence ...
