Airplane! Introducing the cockpit party problem

Record type:

paper

Creator:

PuiBigDev

Editor:

LabBur

Publisher:

CCSD

Host:

International audience BEA is the French authority in charge of safety investigations in the event of a civil aircraft accident, and in this context analyses audio files from cockpit voice recorders (CVRs). The CVR design constraints result in the presence of a large amount of superimposed speech areas, which complicates the use of this data. In this article, we propose a CVR mixture model and present a first study on the potential contribution of Blind Source Separation for improving the intelligibility of CVR recordings.

Visit

hal.science

Tasks

speech processing

Party footprints in Africa: Measuring local party presence across the continent

The conventional view of Africa’s political parties holds that they are organizationally weak

Bridging the Divide: Measuring Party System Change and Classifying Party Systems

Party systems research has proceeded along two parallel lines of inquiry, one predominantly “qualita

Introducing Gorwaa

An overview of the Gorwaa language, based on fieldwork and recordings, for the University of Bayreut

Introducing Arguments

A compositional theory of verbal argument structure that explores how “noncore” arguments are introd

Pulling for the Party: the impact of party foot soldiers on voter behaviour in Zimbabwe’s polarised political space

This project aims to develop and test a theory of how electoral behaviour is determined by parties,

Introducing the Peacekeeping Mandates (PEMA) Dataset

Research on UN peacekeeping operations has established that operations' size and composition affect