Performance and Evaluation

Dia AbuZeina; Moustafa Elshafei

doi:10.1007/978-1-4614-1213-7_6

Performance and Evaluation

Dia AbuZeina^*, Moustafa Elshafei

^*Corresponding author for this work

Department of Industrial and Systems Engineering

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

This chapter presents the results achieved by modeling cross-word pronunciation variation problem of MSA. We practically investigated two MSA phonological rules (Idgham and Iqlaab) which significantly enhanced recognition accuracy. Three ASR’s metrics were measured: word error rate (WER), out of vocabulary (OOV), and perplexity (PP).

Original language	English
Title of host publication	SpringerBriefs in Speech Technology
Publisher	Springer Science and Business Media B.V.
Pages	59-68
Number of pages	10
DOIs	https://doi.org/10.1007/978-1-4614-1213-7_6
State	Published - 2012

Publication series

Name	SpringerBriefs in Speech Technology
ISSN (Print)	2191-737X
ISSN (Electronic)	2191-7388

Bibliographical note

Publisher Copyright:
© 2012, Dia AbuZeina.

Keywords

Baseline System
Compound Word
Language Model
Substitution Error
Word Error Rate

ASJC Scopus subject areas

Electrical and Electronic Engineering
Computer Science Applications
Human-Computer Interaction
Information Systems
Signal Processing

Access to Document

10.1007/978-1-4614-1213-7_6

Cite this

@inbook{e5db73e4147b443faa83bf8ceaa794a6,

title = "Performance and Evaluation",

abstract = "This chapter presents the results achieved by modeling cross-word pronunciation variation problem of MSA. We practically investigated two MSA phonological rules (Idgham and Iqlaab) which significantly enhanced recognition accuracy. Three ASR{\textquoteright}s metrics were measured: word error rate (WER), out of vocabulary (OOV), and perplexity (PP).",

keywords = "Baseline System, Compound Word, Language Model, Substitution Error, Word Error Rate",

author = "Dia AbuZeina and Moustafa Elshafei",

note = "Publisher Copyright: {\textcopyright} 2012, Dia AbuZeina.",

year = "2012",

doi = "10.1007/978-1-4614-1213-7\_6",

language = "English",

series = "SpringerBriefs in Speech Technology",

publisher = "Springer Science and Business Media B.V.",

pages = "59--68",

booktitle = "SpringerBriefs in Speech Technology",

address = "Germany",

}

TY - CHAP

T1 - Performance and Evaluation

AU - AbuZeina, Dia

AU - Elshafei, Moustafa

PY - 2012

Y1 - 2012

N2 - This chapter presents the results achieved by modeling cross-word pronunciation variation problem of MSA. We practically investigated two MSA phonological rules (Idgham and Iqlaab) which significantly enhanced recognition accuracy. Three ASR’s metrics were measured: word error rate (WER), out of vocabulary (OOV), and perplexity (PP).

AB - This chapter presents the results achieved by modeling cross-word pronunciation variation problem of MSA. We practically investigated two MSA phonological rules (Idgham and Iqlaab) which significantly enhanced recognition accuracy. Three ASR’s metrics were measured: word error rate (WER), out of vocabulary (OOV), and perplexity (PP).

KW - Baseline System

KW - Compound Word

KW - Language Model

KW - Substitution Error

KW - Word Error Rate

UR - https://www.scopus.com/pages/publications/85101158541

U2 - 10.1007/978-1-4614-1213-7_6

DO - 10.1007/978-1-4614-1213-7_6

M3 - Chapter

AN - SCOPUS:85101158541

T3 - SpringerBriefs in Speech Technology

SP - 59

EP - 68

BT - SpringerBriefs in Speech Technology

PB - Springer Science and Business Media B.V.

ER -

Performance and Evaluation

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this