A system for dynamic 3D visualisation of speech recognition paths

Satumino Luz; Masood Masoodian; Bill Rogers; Bo Zhang

doi:10.1145/1385569.1385667

A system for dynamic 3D visualisation of speech recognition paths

Satumino Luz^*, Masood Masoodian, Bill Rogers, Bo Zhang

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

Abstract

This paper presents an interactive visualisation system that assists users of semi-automatic speech transcription systems to assess alternative recognition results in real time and provide feedback to the speech recognition back-end in an intuitive manner. This prototype uses the OpenGL libraries to implement an animated 3D visual representation of alternative recognition results generated by the Sphinx automatic speech recognition system. It is expected that displaying alternatives dynamically will facilitate early detection of recognition errors and encourage user interaction, which in turn can be used to improve future recognition performance.

Original language	English
Pages	482-483
Number of pages	2
DOIs	https://doi.org/10.1145/1385569.1385667
Publication status	Published - May 2008
Event	Working Conference on Advanced Visual Interfaces, AVI 08 - Naples, Italy Duration: 28 May 2008 → 30 May 2008

Conference

Conference	Working Conference on Advanced Visual Interfaces, AVI 08
Country/Territory	Italy
City	Naples
Period	28/05/08 → 30/05/08

Keywords / Materials (for Non-textual outputs)

Animated interfaces
Automatic speech transcription
Error correction
Interactive visualisation

Access to Document

10.1145/1385569.1385667

Cite this

@conference{cee224610dc649e586449732555d1d13,

title = "A system for dynamic 3D visualisation of speech recognition paths",

abstract = "This paper presents an interactive visualisation system that assists users of semi-automatic speech transcription systems to assess alternative recognition results in real time and provide feedback to the speech recognition back-end in an intuitive manner. This prototype uses the OpenGL libraries to implement an animated 3D visual representation of alternative recognition results generated by the Sphinx automatic speech recognition system. It is expected that displaying alternatives dynamically will facilitate early detection of recognition errors and encourage user interaction, which in turn can be used to improve future recognition performance.",

keywords = "Animated interfaces, Automatic speech transcription, Error correction, Interactive visualisation",

author = "Satumino Luz and Masood Masoodian and Bill Rogers and Bo Zhang",

year = "2008",

month = may,

doi = "10.1145/1385569.1385667",

language = "English",

pages = "482--483",

note = "Working Conference on Advanced Visual Interfaces, AVI 08 ; Conference date: 28-05-2008 Through 30-05-2008",

}

TY - CONF

T1 - A system for dynamic 3D visualisation of speech recognition paths

AU - Luz, Satumino

AU - Masoodian, Masood

AU - Rogers, Bill

AU - Zhang, Bo

PY - 2008/5

Y1 - 2008/5

N2 - This paper presents an interactive visualisation system that assists users of semi-automatic speech transcription systems to assess alternative recognition results in real time and provide feedback to the speech recognition back-end in an intuitive manner. This prototype uses the OpenGL libraries to implement an animated 3D visual representation of alternative recognition results generated by the Sphinx automatic speech recognition system. It is expected that displaying alternatives dynamically will facilitate early detection of recognition errors and encourage user interaction, which in turn can be used to improve future recognition performance.

AB - This paper presents an interactive visualisation system that assists users of semi-automatic speech transcription systems to assess alternative recognition results in real time and provide feedback to the speech recognition back-end in an intuitive manner. This prototype uses the OpenGL libraries to implement an animated 3D visual representation of alternative recognition results generated by the Sphinx automatic speech recognition system. It is expected that displaying alternatives dynamically will facilitate early detection of recognition errors and encourage user interaction, which in turn can be used to improve future recognition performance.

KW - Animated interfaces

KW - Automatic speech transcription

KW - Error correction

KW - Interactive visualisation

UR - http://www.scopus.com/inward/record.url?scp=57349132532&partnerID=8YFLogxK

U2 - 10.1145/1385569.1385667

DO - 10.1145/1385569.1385667

M3 - Paper

AN - SCOPUS:57349132532

SP - 482

EP - 483

T2 - Working Conference on Advanced Visual Interfaces, AVI 08

Y2 - 28 May 2008 through 30 May 2008

ER -

A system for dynamic 3D visualisation of speech recognition paths

Abstract

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Other files and links

Fingerprint

Cite this