An efficient phoneme distance measure using a lexical tree

Baruchi Har-Lev; Vered Aharonson; Ami Moyal

doi:10.1109/EEEI.2010.5662179

An efficient phoneme distance measure using a lexical tree

Baruchi Har-Lev
, Vered Aharonson
, Ami Moyal

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

Abstract

The high complexity associated with phonetic search processes when using very large lexica, long utterances and huge speech databases has become a vital issue over the last decade. In this paper, we present a novel phonetic search method based on a lexical tree that addresses this problem. The new suggested method was compared to a basic phonetic search using over 2000 utterances from the IBM Voicemail Databases and a 100k word lexicon. Preliminary results show that using a phonetic search based on the suggested tree method, does not degrade the overall recognition performance and reduces computational complexity by 35%.

Original language	English
Title of host publication	2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2010
Pages	464-467
Number of pages	4
DOIs	https://doi.org/10.1109/EEEI.2010.5662179
Publication status	Published - 2010
Externally published	Yes
Event	2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2010 - Eilat, Israel Duration: 17 Nov 2010 → 20 Nov 2010

Publication series

Name	2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2010

Conference

Conference	2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2010
Country/Territory	Israel
City	Eilat
Period	17/11/10 → 20/11/10

Access to Document

10.1109/EEEI.2010.5662179

Cite this

@inproceedings{2134c571da244359aceb1cb412538170,

title = "An efficient phoneme distance measure using a lexical tree",

abstract = "The high complexity associated with phonetic search processes when using very large lexica, long utterances and huge speech databases has become a vital issue over the last decade. In this paper, we present a novel phonetic search method based on a lexical tree that addresses this problem. The new suggested method was compared to a basic phonetic search using over 2000 utterances from the IBM Voicemail Databases and a 100k word lexicon. Preliminary results show that using a phonetic search based on the suggested tree method, does not degrade the overall recognition performance and reduces computational complexity by 35\%.",

author = "Baruchi Har-Lev and Vered Aharonson and Ami Moyal",

year = "2010",

doi = "10.1109/EEEI.2010.5662179",

language = "English",

isbn = "9781424486809",

series = "2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2010",

pages = "464--467",

booktitle = "2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2010",

note = "2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2010 ; Conference date: 17-11-2010 Through 20-11-2010",

}

Har-Lev, B, Aharonson, V & Moyal, A 2010, An efficient phoneme distance measure using a lexical tree. in 2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2010., 5662179, 2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2010, pp. 464-467, 2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2010, Eilat, Israel, 17/11/10. https://doi.org/10.1109/EEEI.2010.5662179

An efficient phoneme distance measure using a lexical tree. / Har-Lev, Baruchi; Aharonson, Vered; Moyal, Ami.
2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2010. 2010. p. 464-467 5662179 (2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2010).

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

TY - GEN

T1 - An efficient phoneme distance measure using a lexical tree

AU - Har-Lev, Baruchi

AU - Aharonson, Vered

AU - Moyal, Ami

PY - 2010

Y1 - 2010

N2 - The high complexity associated with phonetic search processes when using very large lexica, long utterances and huge speech databases has become a vital issue over the last decade. In this paper, we present a novel phonetic search method based on a lexical tree that addresses this problem. The new suggested method was compared to a basic phonetic search using over 2000 utterances from the IBM Voicemail Databases and a 100k word lexicon. Preliminary results show that using a phonetic search based on the suggested tree method, does not degrade the overall recognition performance and reduces computational complexity by 35%.

AB - The high complexity associated with phonetic search processes when using very large lexica, long utterances and huge speech databases has become a vital issue over the last decade. In this paper, we present a novel phonetic search method based on a lexical tree that addresses this problem. The new suggested method was compared to a basic phonetic search using over 2000 utterances from the IBM Voicemail Databases and a 100k word lexicon. Preliminary results show that using a phonetic search based on the suggested tree method, does not degrade the overall recognition performance and reduces computational complexity by 35%.

UR - https://www.scopus.com/pages/publications/78651255614

U2 - 10.1109/EEEI.2010.5662179

DO - 10.1109/EEEI.2010.5662179

M3 - Conference contribution

AN - SCOPUS:78651255614

SN - 9781424486809

T3 - 2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2010

SP - 464

EP - 467

BT - 2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2010

T2 - 2010 IEEE 26th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2010

Y2 - 17 November 2010 through 20 November 2010

ER -

An efficient phoneme distance measure using a lexical tree

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this