Publication

Low-Rank Representation of Nearest Neighbor Phone Posterior Probabilities to Enhance DNN Acoustic Modeling

Related publications (33)

The project introduces an innovative visual method for analysing libraries and archives, with a focus on Bibliotheca Hertziana’s library collection. This collection, which dates back over a century, is examined by integrating user loan data with deep mappi ...

2024

The number of materials or molecules that can be created by combining different chemical elements in various proportions and spatial arrangements is enormous. Computational chemistry can be used to generate databases containing billions of potential struct ...

2020

Neural Network (NN) classifiers can assign extreme probabilities to samples that have not appeared during training (out-of-distribution samples) resulting in erroneous and unreliable predictions. One of the causes for this unwanted behaviour lies in the us ...

IEEE2020

Template-matching for text-dependent speaker verification

Petr Motlicek, Subhadeep Dey

In the last decade, i-vector and Joint Factor Analysis (JFA) approaches to speaker modeling have become ubiquitous in the area of automatic speaker recognition. Both of these techniques involve the computation of posterior probabilities, using either Gauss ...

2017

Low-Rank Representation For Enhanced Deep Neural Network Acoustic Models

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 ...

Idiap2016

Phonetic and Phonological Posterior Search Space Hashing Exploiting Class-Specific Sparsity Structures

Hervé Bourlard, Milos Cernak, Afsaneh Asaei

This paper shows that exemplar-based speech processing using class-conditional posterior probabilities admits a highly effective search strategy relying on posteriors' intrinsic sparsity structures. The posterior probabilities are estimated for phonetic an ...

Idiap2016

Efficient Posterior Exemplar Search Space Hashing Exploiting Class-Specific Sparsity Structures

Hervé Bourlard, Milos Cernak, Afsaneh Asaei

2016

Applying Multi- and Cross-Lingual Stochastic Phone Space Transformations to Non-Native Speech Recognition

Hervé Bourlard, Philip Neil Garner, John David Scott Dines, David Imseng

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 ...

Ieee-Inst Electrical Electronics Engineers Inc2013

Investigation of kNN Classifier on Posterior Features Towards Application in Automatic Speech Recognition

Hervé Bourlard, Afsaneh Asaei, Benjamin Picart

Class posterior distributions can be used to classify or as intermediate features, which can be further exploited in different classifiers (e.g., Gaussian Mixture Models, GMM) towards improving speech recognition performance. In this paper we examine the p ...

Idiap2010

Support Vector Machines with a Reject Option

We consider the problem of binary classification where the classfier may abstain instead of classifying each observation. The Bayes decision rule for this setup, known as Chow’s rule, is deﬁned by two thresholds on posterior probabilities. From simple desi ...

Idiap2009

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.