Publication

Multi-stream ASR: An Oracle Perspective

Hervé Bourlard
2006
Conference Papers

Abstract

Multi-stream based automatic speech recognition (ASR) systems outperform their single stream counterparts, specially in case of noisy speech. The main issues in multi-stream systems are: a) Find the feature streams carrying complementary information, and b) Combine the outputs of the classifiers trained on these feature streams. This paper investigates an `oracle' test to address these issues. An interpretation of the oracle test is proposed that can indicate the complimentary of the feature streams used in a multi-stream system. Also, we investigate the statistical nature of the oracle and study the relationship between oracle selection and entropy at the output of the classifiers. In the experiments carried out on two multi-stream systems, approximately 80% of the time oracle selected the classifier which had the minimum output entropy. The oracle analysis is supported by results obtained on multi-stream systems using different feature streams and inverse entropy method for weighting.

Official source

https://infoscience.epfl.ch/entities/publication/4d444941-f162-49a3-9221-543abce5c557

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Graph Chat

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.

Hervé Bourlard
2006
Conference Papers

Abstract

Official source

https://infoscience.epfl.ch/entities/publication/4d444941-f162-49a3-9221-543abce5c557

About this result

Related concepts (32)

Streaming media

Streaming media is multimedia that is delivered and consumed in a continuous manner from a source, with little or no intermediate storage in network elements. Streaming refers to the delivery method of content, rather than the content itself. Distinguishing delivery method from the media applies specifically to telecommunications networks, as most of the traditional media delivery systems are either inherently streaming (e.g. radio, television) or inherently non-streaming (e.g. books, videotapes, audio CDs).

Stream processing

In computer science, stream processing (also known as event stream processing, data stream processing, or distributed stream processing) is a programming paradigm which views streams, or sequences of events in time, as the central input and output objects of computation. Stream processing encompasses dataflow programming, reactive programming, and distributed data processing. Stream processing systems aim to expose parallel processing for data streams and rely on streaming algorithms for efficient implementation.

Naive Bayes classifier

In statistics, naive Bayes classifiers are a family of simple "probabilistic classifiers" based on applying Bayes' theorem with strong (naive) independence assumptions between the features (see Bayes classifier). They are among the simplest Bayesian network models, but coupled with kernel density estimation, they can achieve high accuracy levels. Naive Bayes classifiers are highly scalable, requiring a number of parameters linear in the number of variables (features/predictors) in a learning problem.

Related publications (10)

Multi-stream ASR: An Oracle Perspective

Chat with Graph Search

A methodological framework for evaluating real-time bioaerosol classification algorithms

Scene Recognition with Naive Bayes Non-linear Learning

Semisupervised segmentation of remote sensing images with active queries.