Publication

KL Realignment for Speaker Diarization with Multiple Feature Streams

Related publications (35)

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-Context Phone Posteriors as Complementary Features for Tandem ASR

Hervé Bourlard, Hamed Ketabdar

In this paper, we present a method for integrating possible prior knowledge (such as phonetic and lexical knowledge), as well as acoustic context (e.g., the whole utterance) in the phone posterior estimation, and we propose to use the obtained posteriors a ...

2008

Enhanced Phone Posteriors for Improving Speech Recognition Systems

Hervé Bourlard, Hamed Ketabdar

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, ...

IDIAP2008

Using KL-based Acoustic Models in a Large Vocabulary Recognition Task

Hervé Bourlard, Guillermo Aradilla

Posterior probabilities of sub-word units have been shown to be an effective front-end for ASR. However, attempts to model this type of features either do not benefit from modeling context-dependent phonemes, or use an inefficient distribution to estimate ...

IDIAP2008

Map-matching for pedestrians via Bayesian inference

Michel Bierlaire, Bertrand Merminod

A navigation process is to start from a known (initial) position and to ensure a continued localisation of the user during the movement. Consider a pedestrian navigation system which contains a GPS receiver and a set of inertial sensors connected with the ...

2006

Multi-stream Processing for Noise Robust Speech Recognition

Hemant Misra

In this thesis, the framework of multi-stream combination has been explored to improve the noise robustness of automatic speech recognition (ASR) systems. The central idea of multi-stream ASR is to combine information from several sources to improve the pe ...

École Polytechnique Fédérale de Lausanne2006

Multi-stream Processing for Noise Robust Speech Recognition

Hemant Misra

IDIAP2006

Multi-stream processing for noise robust speech recognition

Hemant Misra

EPFL2006

Characteristic fragment size distributions in dynamic fragmentation

Jean-François Molinari

The one-dimensional fragmentation of a dynamically expanding ring (Mott's problem) is studied numerically to obtain the fragment signatures under different strain rates. An empirical formula is proposed to calculate an average fragment size. Rayleigh distr ...

2006

Hierarchical Multi-Stream Posterior Based Speech Recognition System

Hervé Bourlard, Samy Bengio, Hamed Ketabdar

In this paper, we present initial results towards boosting posterior based speech recognition systems by estimating more informative posteriors using multiple streams of features and taking into account acoustic context (e.g., as available in the whole utt ...

2005

Hierarchical Multi-Stream Posterior Based Speech Recognition System

Hervé Bourlard, Samy Bengio, Hamed Ketabdar

IDIAP2005