Automatic clinical speech recognition for CLEF 2015 eHealth challenge

Thoai Man Luu, Rob PHAN, Rachel Davey, Girija Chetty

Research output: Contribution to conference (non-published works)Paper

Abstract

In this working notes report/paper, we describe the details of two submis-sions for CLEF 2015 eHealth challenge for Task 1a, with details of methods and tools developed for automatic speech recognition of NICTA synthetic nursing handover dataset. The first method involves a novel zero-resource approach based on unsuper-vised acoustic only modeling of speech involving word discovery, and the second method is based on combination of acoustic, language, grammar and dictionary models, using well known open source speech recognition toolkit from CMU, the CMU Sphinx[7]. The experimental evaluation of the two methods was done on Challenge dataset (NICTA synthetic nursing handover dataset).

Original languageEnglish
Pages1-14
Number of pages14
Publication statusPublished - 2015

Fingerprint

Nursing
Speech recognition
Acoustics
Glossaries

Cite this

@conference{1dce43d943b84d1c8099fafa607ef172,
title = "Automatic clinical speech recognition for CLEF 2015 eHealth challenge",
abstract = "In this working notes report/paper, we describe the details of two submis-sions for CLEF 2015 eHealth challenge for Task 1a, with details of methods and tools developed for automatic speech recognition of NICTA synthetic nursing handover dataset. The first method involves a novel zero-resource approach based on unsuper-vised acoustic only modeling of speech involving word discovery, and the second method is based on combination of acoustic, language, grammar and dictionary models, using well known open source speech recognition toolkit from CMU, the CMU Sphinx[7]. The experimental evaluation of the two methods was done on Challenge dataset (NICTA synthetic nursing handover dataset).",
author = "Luu, {Thoai Man} and Rob PHAN and Rachel Davey and Girija Chetty",
year = "2015",
language = "English",
pages = "1--14",

}

Automatic clinical speech recognition for CLEF 2015 eHealth challenge. / Luu, Thoai Man; PHAN, Rob; Davey, Rachel; Chetty, Girija.

2015. 1-14.

Research output: Contribution to conference (non-published works)Paper

TY - CONF

T1 - Automatic clinical speech recognition for CLEF 2015 eHealth challenge

AU - Luu, Thoai Man

AU - PHAN, Rob

AU - Davey, Rachel

AU - Chetty, Girija

PY - 2015

Y1 - 2015

N2 - In this working notes report/paper, we describe the details of two submis-sions for CLEF 2015 eHealth challenge for Task 1a, with details of methods and tools developed for automatic speech recognition of NICTA synthetic nursing handover dataset. The first method involves a novel zero-resource approach based on unsuper-vised acoustic only modeling of speech involving word discovery, and the second method is based on combination of acoustic, language, grammar and dictionary models, using well known open source speech recognition toolkit from CMU, the CMU Sphinx[7]. The experimental evaluation of the two methods was done on Challenge dataset (NICTA synthetic nursing handover dataset).

AB - In this working notes report/paper, we describe the details of two submis-sions for CLEF 2015 eHealth challenge for Task 1a, with details of methods and tools developed for automatic speech recognition of NICTA synthetic nursing handover dataset. The first method involves a novel zero-resource approach based on unsuper-vised acoustic only modeling of speech involving word discovery, and the second method is based on combination of acoustic, language, grammar and dictionary models, using well known open source speech recognition toolkit from CMU, the CMU Sphinx[7]. The experimental evaluation of the two methods was done on Challenge dataset (NICTA synthetic nursing handover dataset).

UR - http://www.scopus.com/inward/record.url?scp=84982798814&partnerID=8YFLogxK

M3 - Paper

SP - 1

EP - 14

ER -