English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  A two-pass strategy for handling OOVs in a large vocabulary recognition task

Scharenborg, O., & Seneff, S. (2005). A two-pass strategy for handling OOVs in a large vocabulary recognition task. In Interspeech'2005 - Eurospeech, 9th European Conference on Speech Communication and Technology, (pp. 1669-1672). ISCA Archive.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0012-D235-F Version Permalink: https://hdl.handle.net/11858/00-001M-0000-0012-D236-D
Genre: Conference Paper

Files

show Files
hide Files
:
12116927d01.pdf (Publisher version), 120KB
View   Save
File Permalink:
https://hdl.handle.net/11858/00-001M-0000-0012-D234-2
Name:
12116927d01.pdf
Description:
-
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
View
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Scharenborg, Odette1, Author           
Seneff, S.2, Author
Affiliations:
1CLST, Radboud University Nijmegen, Nijmegen, The Netherlands, ou_persistent22              
2Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: This paper addresses the issue of large-vocabulary recognition in a specific word class. We propose a two-pass strategy in which only major cities are explicitly represented in the first stage lexicon. An unknown word model encoded as a phone loop is used to detect OOV city names (referred to as rare city names). After which SpeM, a tool that can extract words and word-initial cohorts from phone graphs on the basis of a large fallback lexicon, provides an N-best list of promising city names on the basis of the phone sequences generated in the first stage. This N-best list is then inserted into the second stage lexicon for a subsequent recognition pass. Experiments were conducted on a set of spontaneous telephone-quality utterances each containing one rare city name. We tested the size of the N-best list and three types of language models (LMs). The experiments showed that SpeM was able to include nearly 85% of the correct city names into an N-best list of 3000 city names when a unigram LM, which also boosted the unigram scores of a city name in a given state, was used.

Details

show
hide
Language(s): eng - English
 Dates: 2005
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: Interspeech'2005 - Eurospeech, 9th European Conference on Speech Communication and Technology,
Place of Event: Lisbon, Portugal
Start-/End Date: 2005-09-04 - 2005-09-08

Legal Case

show

Project information

show

Source 1

show
hide
Title: Interspeech'2005 - Eurospeech, 9th European Conference on Speech Communication and Technology,
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: ISCA Archive
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 1669 - 1672 Identifier: URI: http://www.isca-speech.org/archive/interspeech_2005