A high performance Mandarin digit recognizer

Zang Bo, Liu Juan, Peng Gang, William Shi Yuan Wang

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

1 Citation (Scopus)

Abstract

Digit recognition is important in some applications such as automated banking systems or database information retrieving systems. To design a high performance Mandarin digit recognizer, a Mandarin phonetic question set was first carefully designed and then used to cluster 846 gender dependent cross word triphones. To model the fine differences in high frequency region of Mandarin initials, inverse mel-frequency warping was used to calculate the IMFCC feature. The IMFCC feature was shown to be quite effective in recovering the substitution errors caused by similarity of the Mandarin initials. Combined with triphone duration modeling, the recognizer produced 98.81% word accuracy rate and 95.20% sentence correct rate.
Original languageEnglish
Title of host publicationISSPA 1999 - Proceedings of the 5th International Symposium on Signal Processing and Its Applications
PublisherIEEE Computer Society
Pages629-632
Number of pages4
Volume2
ISBN (Print)1864354518, 9781864354515
DOIs
Publication statusPublished - 1 Jan 1999
Externally publishedYes
Event5th International Symposium on Signal Processing and Its Applications, ISSPA 1999 - Brisbane, QLD, Australia
Duration: 22 Aug 199925 Aug 1999

Conference

Conference5th International Symposium on Signal Processing and Its Applications, ISSPA 1999
CountryAustralia
CityBrisbane, QLD
Period22/08/9925/08/99

ASJC Scopus subject areas

  • Signal Processing

Cite this