Posterior-Based Features and Distances in Template Matching for Speech Recognition
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.
In order to model a broader range of phenomena taking place in three-dimensional plasmas, the LEMan code has been extended to a warm formulation. As the wave propagation is strongly influenced by the parallel wave vector, special attention has been paid fo ...
In this thesis, we investigate a hierarchical approach for estimating the phonetic class-conditional probabilities using a multilayer perceptron (MLP) neural network. The architecture consists of two MLP classifiers in cascade. The first MLP is trained in ...
In high-speed dry milling of thin-walled parts, the cutter-workpiece temperature rises asymptotically with cutting speed, causing excessive cutter tooth wear and workpiece thermal expansion, which in turn reduces the cutter life and produces dimensional an ...
Dispersal is often viewed as a process on which the landscape has little effect. This is particularly apparent in populations’ genetic and ecological studies, where isolation by distance is generally tested using a Euclidean distance between populations. H ...
In this paper, we present a new approach towards high performance speech/music discrimination on realistic tasks related to the automatic transcription of broadcast news. In the approach presented here, the (local) Probability Density Function (PDF) estima ...
The use of large speech corpora in example-based approaches for speech recognition is mainly focused on increasing the number of examples. This strategy presents some difficulties because databases may not provide enough examples for some rare words. In th ...
This paper presents our approach for automatic speech recognition (ASR) of overlapping speech. Our system consists of two principal components: a speech separation component and a feature estmation component. In the speech separation phase, we first estima ...
Using phone posterior probabilities has been increasingly explored for improving automatic speech recognition (ASR) systems. In this paper, we propose two approaches for hierarchically enhancing these phone posteriors, by integrating long acoustic context, ...
In this paper, we present a new approach towards high performance speech/music discrimination on realistic tasks related to the automatic transcription of broadcast news. In the approach presented here, the (local) Probability Density Function (PDF) estima ...
In this paper we apply the Full Combination (FC) multi-band approach, which has originally been introduced in the framework of posterior-based HMM/ANN (Hidden Markov Model/Artificial Neural Network) hybrid systems, to systems in which the ANN (or Multilaye ...
